< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 34 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')



Text #0

Max Range: 3.5178. Min Range: -3.5178

Max Act: 3.5178. Min Act: -0.1700

Data Index: 5635956 (The Pile)

Max Activating Token Index: 278

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.5178. Min Range: -3.5178

Max Act: 3.3140. Min Act: -0.1700

Data Index: 614793 (The Pile)

Max Activating Token Index: 950

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.5178. Min Range: -3.5178

Max Act: 3.3454. Min Act: -0.1700

Data Index: 5634796 (The Pile)

Max Activating Token Index: 486

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.5178. Min Range: -3.5178

Max Act: 3.2826. Min Act: -0.1700

Data Index: 3138183 (The Pile)

Max Activating Token Index: 917

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.5178. Min Range: -3.5178

Max Act: 3.3140. Min Act: -0.1700

Data Index: 5777323 (The Pile)

Max Activating Token Index: 483

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.5178. Min Range: -3.5178

Max Act: 3.4081. Min Act: -0.1700

Data Index: 1788486 (The Pile)

Max Activating Token Index: 248

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.5178. Min Range: -3.5178

Max Act: 3.4081. Min Act: -0.1700

Data Index: 1025682 (The Pile)

Max Activating Token Index: 595

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.5178. Min Range: -3.5178

Max Act: 3.3297. Min Act: -0.1700

Data Index: 4827100 (The Pile)

Max Activating Token Index: 910

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.5178. Min Range: -3.5178

Max Act: 3.2826. Min Act: -0.1700

Data Index: 4755407 (The Pile)

Max Activating Token Index: 1009

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.5178. Min Range: -3.5178

Max Act: 3.3297. Min Act: -0.1700

Data Index: 4104136 (The Pile)

Max Activating Token Index: 195

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.5178. Min Range: -3.5178

Max Act: 3.3140. Min Act: -0.1700

Data Index: 6986017 (The Pile)

Max Activating Token Index: 771

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.5178. Min Range: -3.5178

Max Act: 3.3454. Min Act: -0.1700

Data Index: 5987785 (The Pile)

Max Activating Token Index: 515

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.5178. Min Range: -3.5178

Max Act: 3.3454. Min Act: -0.1700

Data Index: 10607277 (The Pile)

Max Activating Token Index: 994

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.5178. Min Range: -3.5178

Max Act: 3.3454. Min Act: -0.1700

Data Index: 10642320 (The Pile)

Max Activating Token Index: 764

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.5178. Min Range: -3.5178

Max Act: 3.2826. Min Act: -0.1700

Data Index: 7095118 (The Pile)

Max Activating Token Index: 662

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.5178. Min Range: -3.5178

Max Act: 3.2197. Min Act: -0.1700

Data Index: 7391034 (The Pile)

Max Activating Token Index: 559

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.5178. Min Range: -3.5178

Max Act: 3.3140. Min Act: -0.1700

Data Index: 4324810 (The Pile)

Max Activating Token Index: 688

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.5178. Min Range: -3.5178

Max Act: 3.3611. Min Act: -0.1700

Data Index: 3477761 (The Pile)

Max Activating Token Index: 677

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.5178. Min Range: -3.5178

Max Act: 3.2983. Min Act: -0.1700

Data Index: 7341284 (The Pile)

Max Activating Token Index: 516

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.5178. Min Range: -3.5178

Max Act: 3.2826. Min Act: -0.1700

Data Index: 4815696 (The Pile)

Max Activating Token Index: 477

Click toggle to see full text

Truncated

Full Text #19