Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 969 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0364. Min Act: -0.0004

Data Index: 1388406 (Python Code)

Max Activating Token Index: 853

Text #1

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0268. Min Act: -0.0004

Data Index: 1580652 (Python Code)

Max Activating Token Index: 180

Text #2

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0209. Min Act: -0.0004

Data Index: 1465580 (Python Code)

Max Activating Token Index: 893

Text #3

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0191. Min Act: -0.0004

Data Index: 1624608 (Python Code)

Max Activating Token Index: 775

Text #4

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0197. Min Act: -0.0004

Data Index: 620408 (C4 (Web Text))

Max Activating Token Index: 859

Text #5

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0189. Min Act: -0.0004

Data Index: 1553906 (Python Code)

Max Activating Token Index: 1020

Text #6

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0193. Min Act: -0.0004

Data Index: 1507328 (Python Code)

Max Activating Token Index: 914

Text #7

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0185. Min Act: -0.0004

Data Index: 1608414 (Python Code)

Max Activating Token Index: 310

Text #8

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0177. Min Act: -0.0004

Data Index: 952566 (C4 (Web Text))

Max Activating Token Index: 366

Text #9

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0178. Min Act: -0.0004

Data Index: 1621218 (Python Code)

Max Activating Token Index: 203

Text #10

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0169. Min Act: -0.0004

Data Index: 357453 (C4 (Web Text))

Max Activating Token Index: 701

Text #11

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0173. Min Act: -0.0004

Data Index: 1648923 (Python Code)

Max Activating Token Index: 852

Text #12

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0166. Min Act: -0.0004

Data Index: 1419915 (Python Code)

Max Activating Token Index: 780

Text #13

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0167. Min Act: -0.0004

Data Index: 1211023 (C4 (Web Text))

Max Activating Token Index: 504

Text #14

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0171. Min Act: -0.0004

Data Index: 1490101 (Python Code)

Max Activating Token Index: 919

Text #15

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0168. Min Act: -0.0004

Data Index: 1541661 (Python Code)

Max Activating Token Index: 769

Text #16

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0168. Min Act: -0.0004

Data Index: 771537 (C4 (Web Text))

Max Activating Token Index: 898

Text #17

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0166. Min Act: -0.0004

Data Index: 172466 (C4 (Web Text))

Max Activating Token Index: 549

Text #18

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0159. Min Act: -0.0004

Data Index: 634947 (C4 (Web Text))

Max Activating Token Index: 888

Text #19

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0161. Min Act: -0.0004

Data Index: 1441431 (Python Code)

Max Activating Token Index: 983