< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 1128 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.6813. Min Range: -3.6813

Max Act: 3.6813. Min Act: -0.1700

Data Index: 5919453 (The Pile)

Max Activating Token Index: 146

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.6813. Min Range: -3.6813

Max Act: 3.5717. Min Act: -0.1700

Data Index: 7393982 (The Pile)

Max Activating Token Index: 175

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.6813. Min Range: -3.6813

Max Act: 3.5404. Min Act: -0.1700

Data Index: 5726749 (The Pile)

Max Activating Token Index: 168

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.6813. Min Range: -3.6813

Max Act: 3.4934. Min Act: -0.1700

Data Index: 7853303 (The Pile)

Max Activating Token Index: 292

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.6813. Min Range: -3.6813

Max Act: 3.5404. Min Act: -0.1700

Data Index: 7367030 (The Pile)

Max Activating Token Index: 544

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.6813. Min Range: -3.6813

Max Act: 3.5091. Min Act: -0.1700

Data Index: 4811648 (The Pile)

Max Activating Token Index: 337

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.6813. Min Range: -3.6813

Max Act: 3.4464. Min Act: -0.1700

Data Index: 9649101 (The Pile)

Max Activating Token Index: 81

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.6813. Min Range: -3.6813

Max Act: 3.4150. Min Act: -0.1700

Data Index: 3710535 (The Pile)

Max Activating Token Index: 612

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.6813. Min Range: -3.6813

Max Act: 3.4934. Min Act: -0.1700

Data Index: 9920603 (The Pile)

Max Activating Token Index: 166

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.6813. Min Range: -3.6813

Max Act: 3.4621. Min Act: -0.1700

Data Index: 3889874 (The Pile)

Max Activating Token Index: 779

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.6813. Min Range: -3.6813

Max Act: 3.4464. Min Act: -0.1700

Data Index: 4194671 (The Pile)

Max Activating Token Index: 176

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.6813. Min Range: -3.6813

Max Act: 3.4307. Min Act: -0.1700

Data Index: 498259 (The Pile)

Max Activating Token Index: 852

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.6813. Min Range: -3.6813

Max Act: 3.4464. Min Act: -0.1700

Data Index: 1166791 (The Pile)

Max Activating Token Index: 332

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.6813. Min Range: -3.6813

Max Act: 3.4777. Min Act: -0.1700

Data Index: 10575466 (The Pile)

Max Activating Token Index: 208

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.6813. Min Range: -3.6813

Max Act: 3.4150. Min Act: -0.1700

Data Index: 975473 (The Pile)

Max Activating Token Index: 188

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.6813. Min Range: -3.6813

Max Act: 3.3523. Min Act: -0.1700

Data Index: 5505115 (The Pile)

Max Activating Token Index: 906

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.6813. Min Range: -3.6813

Max Act: 3.4307. Min Act: -0.1700

Data Index: 6234358 (The Pile)

Max Activating Token Index: 361

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.6813. Min Range: -3.6813

Max Act: 3.3993. Min Act: -0.1700

Data Index: 7663659 (The Pile)

Max Activating Token Index: 820

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.6813. Min Range: -3.6813

Max Act: 3.4150. Min Act: -0.1700

Data Index: 4729567 (The Pile)

Max Activating Token Index: 167

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.6813. Min Range: -3.6813

Max Act: 3.4150. Min Act: -0.1700

Data Index: 8068464 (The Pile)

Max Activating Token Index: 365

Click toggle to see full text

Truncated

Full Text #19