< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 4034 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')



Text #0

Max Range: 4.2362. Min Range: -4.2362

Max Act: 4.2362. Min Act: -0.1700

Data Index: 9579249 (The Pile)

Max Activating Token Index: 160

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.2362. Min Range: -4.2362

Max Act: 4.1425. Min Act: -0.1700

Data Index: 2324954 (The Pile)

Max Activating Token Index: 380

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.2362. Min Range: -4.2362

Max Act: 4.1112. Min Act: -0.1700

Data Index: 4829815 (The Pile)

Max Activating Token Index: 662

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.2362. Min Range: -4.2362

Max Act: 4.0487. Min Act: -0.1700

Data Index: 5915562 (The Pile)

Max Activating Token Index: 99

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.2362. Min Range: -4.2362

Max Act: 4.0174. Min Act: -0.1700

Data Index: 2734919 (The Pile)

Max Activating Token Index: 154

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.2362. Min Range: -4.2362

Max Act: 4.0174. Min Act: -0.1700

Data Index: 9375007 (The Pile)

Max Activating Token Index: 581

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.2362. Min Range: -4.2362

Max Act: 4.0174. Min Act: -0.1700

Data Index: 1664211 (The Pile)

Max Activating Token Index: 500

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.2362. Min Range: -4.2362

Max Act: 3.9861. Min Act: -0.1700

Data Index: 9787050 (The Pile)

Max Activating Token Index: 802

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.2362. Min Range: -4.2362

Max Act: 3.9861. Min Act: -0.1700

Data Index: 1089814 (The Pile)

Max Activating Token Index: 20

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.2362. Min Range: -4.2362

Max Act: 3.9861. Min Act: -0.1700

Data Index: 9118937 (The Pile)

Max Activating Token Index: 221

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.2362. Min Range: -4.2362

Max Act: 3.9861. Min Act: -0.1700

Data Index: 10653072 (The Pile)

Max Activating Token Index: 183

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.2362. Min Range: -4.2362

Max Act: 3.9861. Min Act: -0.1700

Data Index: 10577990 (The Pile)

Max Activating Token Index: 13

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.2362. Min Range: -4.2362

Max Act: 3.9705. Min Act: -0.1700

Data Index: 4284041 (The Pile)

Max Activating Token Index: 42

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.2362. Min Range: -4.2362

Max Act: 3.9705. Min Act: -0.1700

Data Index: 2891457 (The Pile)

Max Activating Token Index: 853

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.2362. Min Range: -4.2362

Max Act: 3.9705. Min Act: -0.1700

Data Index: 627923 (The Pile)

Max Activating Token Index: 385

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.2362. Min Range: -4.2362

Max Act: 3.9705. Min Act: -0.1700

Data Index: 7141434 (The Pile)

Max Activating Token Index: 98

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.2362. Min Range: -4.2362

Max Act: 3.9705. Min Act: -0.1700

Data Index: 5727923 (The Pile)

Max Activating Token Index: 194

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.2362. Min Range: -4.2362

Max Act: 3.9705. Min Act: -0.1700

Data Index: 7788793 (The Pile)

Max Activating Token Index: 467

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.2362. Min Range: -4.2362

Max Act: 3.9705. Min Act: -0.1700

Data Index: 7440434 (The Pile)

Max Activating Token Index: 649

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.2362. Min Range: -4.2362

Max Act: 3.9549. Min Act: -0.1700

Data Index: 1223359 (The Pile)

Max Activating Token Index: 161

Click toggle to see full text

Truncated

Full Text #19