Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3429 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.4751. Min Range: -1.4751

Max Act: 1.4751. Min Act: -0.0000

Data Index: 341423 (The Pile)

Max Activating Token Index: 167

Text #1

Max Range: 1.4751. Min Range: -1.4751

Max Act: 1.1603. Min Act: -0.0000

Data Index: 875554 (The Pile)

Max Activating Token Index: 109

Text #2

Max Range: 1.4751. Min Range: -1.4751

Max Act: 1.3017. Min Act: -0.0000

Data Index: 174556 (The Pile)

Max Activating Token Index: 882

Text #3

Max Range: 1.4751. Min Range: -1.4751

Max Act: 0.9156. Min Act: -0.0000

Data Index: 1636940 (The Pile)

Max Activating Token Index: 975

Text #4

Max Range: 1.4751. Min Range: -1.4751

Max Act: 0.9655. Min Act: -0.0000

Data Index: 1086705 (The Pile)

Max Activating Token Index: 626

Text #5

Max Range: 1.4751. Min Range: -1.4751

Max Act: 0.8386. Min Act: -0.0000

Data Index: 370383 (The Pile)

Max Activating Token Index: 484

Text #6

Max Range: 1.4751. Min Range: -1.4751

Max Act: 0.8868. Min Act: -0.0000

Data Index: 1152398 (The Pile)

Max Activating Token Index: 261

Text #7

Max Range: 1.4751. Min Range: -1.4751

Max Act: 0.8730. Min Act: -0.0000

Data Index: 121180 (The Pile)

Max Activating Token Index: 227

Text #8

Max Range: 1.4751. Min Range: -1.4751

Max Act: 0.8653. Min Act: -0.0000

Data Index: 220384 (The Pile)

Max Activating Token Index: 248

Text #9

Max Range: 1.4751. Min Range: -1.4751

Max Act: 0.8183. Min Act: -0.0000

Data Index: 32024 (The Pile)

Max Activating Token Index: 363

Text #10

Max Range: 1.4751. Min Range: -1.4751

Max Act: 0.8085. Min Act: -0.0000

Data Index: 1862487 (The Pile)

Max Activating Token Index: 91

Text #11

Max Range: 1.4751. Min Range: -1.4751

Max Act: 0.8044. Min Act: -0.0000

Data Index: 1849423 (The Pile)

Max Activating Token Index: 711

Text #12

Max Range: 1.4751. Min Range: -1.4751

Max Act: 0.7819. Min Act: -0.0000

Data Index: 881328 (The Pile)

Max Activating Token Index: 107

Text #13

Max Range: 1.4751. Min Range: -1.4751

Max Act: 0.7260. Min Act: -0.0000

Data Index: 1958468 (The Pile)

Max Activating Token Index: 1022

Text #14

Max Range: 1.4751. Min Range: -1.4751

Max Act: 0.7145. Min Act: -0.0000

Data Index: 630650 (The Pile)

Max Activating Token Index: 142

Text #15

Max Range: 1.4751. Min Range: -1.4751

Max Act: 0.6858. Min Act: 0.0001

Data Index: 1556169 (The Pile)

Max Activating Token Index: 619

Text #16

Max Range: 1.4751. Min Range: -1.4751

Max Act: 0.7391. Min Act: -0.0000

Data Index: 1371535 (The Pile)

Max Activating Token Index: 242

Text #17

Max Range: 1.4751. Min Range: -1.4751

Max Act: 0.7397. Min Act: -0.0000

Data Index: 289919 (The Pile)

Max Activating Token Index: 24

Text #18

Max Range: 1.4751. Min Range: -1.4751

Max Act: 0.7024. Min Act: 0.0000

Data Index: 1113054 (The Pile)

Max Activating Token Index: 614

Text #19

Max Range: 1.4751. Min Range: -1.4751

Max Act: 0.7263. Min Act: -0.0000

Data Index: 1065746 (The Pile)

Max Activating Token Index: 94