Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4093 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3938. Min Range: -0.3938

Max Act: 0.3610. Min Act: -0.0001

Data Index: 1505301 (Python Code)

Max Activating Token Index: 391

Text #1

Max Range: 0.3938. Min Range: -0.3938

Max Act: 0.3873. Min Act: -0.0001

Data Index: 243580 (C4 (Web Text))

Max Activating Token Index: 565

Text #2

Max Range: 0.3938. Min Range: -0.3938

Max Act: 0.3938. Min Act: -0.0001

Data Index: 1436778 (Python Code)

Max Activating Token Index: 995

Text #3

Max Range: 0.3938. Min Range: -0.3938

Max Act: 0.3527. Min Act: -0.0000

Data Index: 800816 (C4 (Web Text))

Max Activating Token Index: 1008

Text #4

Max Range: 0.3938. Min Range: -0.3938

Max Act: 0.3307. Min Act: -0.0001

Data Index: 1587888 (Python Code)

Max Activating Token Index: 607

Text #5

Max Range: 0.3938. Min Range: -0.3938

Max Act: 0.3388. Min Act: -0.0000

Data Index: 578305 (C4 (Web Text))

Max Activating Token Index: 733

Text #6

Max Range: 0.3938. Min Range: -0.3938

Max Act: 0.3503. Min Act: -0.0001

Data Index: 1485859 (Python Code)

Max Activating Token Index: 553

Text #7

Max Range: 0.3938. Min Range: -0.3938

Max Act: 0.3336. Min Act: -0.0001

Data Index: 1403241 (Python Code)

Max Activating Token Index: 53

Text #8

Max Range: 0.3938. Min Range: -0.3938

Max Act: 0.3205. Min Act: -0.0000

Data Index: 1475802 (Python Code)

Max Activating Token Index: 179

Text #9

Max Range: 0.3938. Min Range: -0.3938

Max Act: 0.3423. Min Act: -0.0001

Data Index: 1389259 (Python Code)

Max Activating Token Index: 485

Text #10

Max Range: 0.3938. Min Range: -0.3938

Max Act: 0.3307. Min Act: -0.0000

Data Index: 1319230 (C4 (Web Text))

Max Activating Token Index: 623

Text #11

Max Range: 0.3938. Min Range: -0.3938

Max Act: 0.3271. Min Act: -0.0001

Data Index: 1242018 (C4 (Web Text))

Max Activating Token Index: 479

Text #12

Max Range: 0.3938. Min Range: -0.3938

Max Act: 0.3156. Min Act: -0.0001

Data Index: 1597200 (Python Code)

Max Activating Token Index: 23

Text #13

Max Range: 0.3938. Min Range: -0.3938

Max Act: 0.3363. Min Act: -0.0001

Data Index: 1399240 (Python Code)

Max Activating Token Index: 324

Text #14

Max Range: 0.3938. Min Range: -0.3938

Max Act: 0.3362. Min Act: -0.0000

Data Index: 1007198 (C4 (Web Text))

Max Activating Token Index: 756

Text #15

Max Range: 0.3938. Min Range: -0.3938

Max Act: 0.3144. Min Act: -0.0001

Data Index: 1562924 (Python Code)

Max Activating Token Index: 907

Text #16

Max Range: 0.3938. Min Range: -0.3938

Max Act: 0.3131. Min Act: -0.0001

Data Index: 1514238 (Python Code)

Max Activating Token Index: 592

Text #17

Max Range: 0.3938. Min Range: -0.3938

Max Act: 0.3224. Min Act: -0.0001

Data Index: 1426132 (Python Code)

Max Activating Token Index: 278

Text #18

Max Range: 0.3938. Min Range: -0.3938

Max Act: 0.3070. Min Act: -0.0000

Data Index: 1120855 (C4 (Web Text))

Max Activating Token Index: 636

Text #19

Max Range: 0.3938. Min Range: -0.3938

Max Act: 0.3165. Min Act: -0.0000

Data Index: 884434 (C4 (Web Text))

Max Activating Token Index: 259