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

Dataset: The Pile

Neuron 935 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: 1.0278. Min Range: -1.0278

Max Act: 1.0278. Min Act: -0.0000

Data Index: 1090973 (The Pile)

Max Activating Token Index: 473

Text #1

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.7498. Min Act: -0.0000

Data Index: 486695 (The Pile)

Max Activating Token Index: 755

Text #2

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.6946. Min Act: -0.0000

Data Index: 911955 (The Pile)

Max Activating Token Index: 924

Text #3

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.7205. Min Act: -0.0000

Data Index: 1520174 (The Pile)

Max Activating Token Index: 665

Text #4

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.6349. Min Act: -0.0000

Data Index: 202032 (The Pile)

Max Activating Token Index: 271

Text #5

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.6255. Min Act: -0.0000

Data Index: 1136804 (The Pile)

Max Activating Token Index: 72

Text #6

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.5862. Min Act: -0.0000

Data Index: 209540 (The Pile)

Max Activating Token Index: 442

Text #7

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.6108. Min Act: -0.0000

Data Index: 1816314 (The Pile)

Max Activating Token Index: 210

Text #8

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.5677. Min Act: -0.0000

Data Index: 317633 (The Pile)

Max Activating Token Index: 993

Text #9

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.6021. Min Act: -0.0000

Data Index: 476283 (The Pile)

Max Activating Token Index: 496

Text #10

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.6152. Min Act: -0.0000

Data Index: 172504 (The Pile)

Max Activating Token Index: 952

Text #11

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.6031. Min Act: -0.0000

Data Index: 1309796 (The Pile)

Max Activating Token Index: 973

Text #12

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.5538. Min Act: -0.0000

Data Index: 1783791 (The Pile)

Max Activating Token Index: 1010

Text #13

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.5922. Min Act: -0.0000

Data Index: 320081 (The Pile)

Max Activating Token Index: 313

Text #14

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.5629. Min Act: -0.0000

Data Index: 1009542 (The Pile)

Max Activating Token Index: 319

Text #15

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.6137. Min Act: -0.0000

Data Index: 1302193 (The Pile)

Max Activating Token Index: 179

Text #16

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.6074. Min Act: -0.0000

Data Index: 965772 (The Pile)

Max Activating Token Index: 510

Text #17

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.5946. Min Act: -0.0000

Data Index: 936509 (The Pile)

Max Activating Token Index: 808

Text #18

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.5898. Min Act: -0.0000

Data Index: 1454999 (The Pile)

Max Activating Token Index: 622

Text #19

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.5714. Min Act: -0.0000

Data Index: 1701952 (The Pile)

Max Activating Token Index: 118