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

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

Neuron 1264 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.2416. Min Act: -0.0001

Data Index: 258341 (C4 (Web Text))

Max Activating Token Index: 51

Text #1

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.2454. Min Act: -0.0001

Data Index: 443452 (C4 (Web Text))

Max Activating Token Index: 943

Text #2

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.2394. Min Act: -0.0000

Data Index: 532328 (C4 (Web Text))

Max Activating Token Index: 809

Text #3

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.2448. Min Act: -0.0001

Data Index: 199397 (C4 (Web Text))

Max Activating Token Index: 920

Text #4

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.2427. Min Act: -0.0001

Data Index: 910743 (C4 (Web Text))

Max Activating Token Index: 974

Text #5

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.2243. Min Act: -0.0001

Data Index: 216789 (C4 (Web Text))

Max Activating Token Index: 808

Text #6

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.2288. Min Act: -0.0000

Data Index: 1288647 (C4 (Web Text))

Max Activating Token Index: 252

Text #7

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.2140. Min Act: -0.0001

Data Index: 1292547 (C4 (Web Text))

Max Activating Token Index: 903

Text #8

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.2178. Min Act: -0.0001

Data Index: 1168446 (C4 (Web Text))

Max Activating Token Index: 694

Text #9

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.2311. Min Act: -0.0001

Data Index: 391572 (C4 (Web Text))

Max Activating Token Index: 967

Text #10

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.2477. Min Act: -0.0001

Data Index: 1210432 (C4 (Web Text))

Max Activating Token Index: 1007

Text #11

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.2261. Min Act: -0.0001

Data Index: 683310 (C4 (Web Text))

Max Activating Token Index: 973

Text #12

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.2162. Min Act: -0.0001

Data Index: 257528 (C4 (Web Text))

Max Activating Token Index: 770

Text #13

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.2222. Min Act: -0.0000

Data Index: 454646 (C4 (Web Text))

Max Activating Token Index: 68

Text #14

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.2242. Min Act: -0.0000

Data Index: 452537 (C4 (Web Text))

Max Activating Token Index: 808

Text #15

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.2136. Min Act: -0.0001

Data Index: 414122 (C4 (Web Text))

Max Activating Token Index: 196

Text #16

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.2065. Min Act: -0.0000

Data Index: 1320685 (C4 (Web Text))

Max Activating Token Index: 207

Text #17

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.2281. Min Act: -0.0001

Data Index: 378329 (C4 (Web Text))

Max Activating Token Index: 180

Text #18

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.2184. Min Act: -0.0001

Data Index: 908950 (C4 (Web Text))

Max Activating Token Index: 752

Text #19

Max Range: 0.2477. Min Range: -0.2477

Max Act: 0.2243. Min Act: -0.0001

Data Index: 705284 (C4 (Web Text))

Max Activating Token Index: 780