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

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

Neuron 3720 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1329. Min Act: -0.0001

Data Index: 1319890 (C4 (Web Text))

Max Activating Token Index: 581

Text #1

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1461. Min Act: -0.0001

Data Index: 358844 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1596. Min Act: -0.0001

Data Index: 1303817 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1487. Min Act: -0.0001

Data Index: 594828 (C4 (Web Text))

Max Activating Token Index: 415

Text #4

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1377. Min Act: -0.0001

Data Index: 1226848 (C4 (Web Text))

Max Activating Token Index: 205

Text #5

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1258. Min Act: -0.0001

Data Index: 136282 (C4 (Web Text))

Max Activating Token Index: 556

Text #6

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1255. Min Act: -0.0001

Data Index: 1337878 (C4 (Web Text))

Max Activating Token Index: 467

Text #7

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1227. Min Act: -0.0001

Data Index: 898254 (C4 (Web Text))

Max Activating Token Index: 78

Text #8

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1389. Min Act: -0.0001

Data Index: 108640 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1439. Min Act: -0.0001

Data Index: 1139658 (C4 (Web Text))

Max Activating Token Index: 716

Text #10

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1098. Min Act: -0.0001

Data Index: 643173 (C4 (Web Text))

Max Activating Token Index: 325

Text #11

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1325. Min Act: -0.0001

Data Index: 1200635 (C4 (Web Text))

Max Activating Token Index: 884

Text #12

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1224. Min Act: -0.0001

Data Index: 277658 (C4 (Web Text))

Max Activating Token Index: 982

Text #13

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1355. Min Act: -0.0001

Data Index: 988836 (C4 (Web Text))

Max Activating Token Index: 380

Text #14

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1262. Min Act: -0.0001

Data Index: 707491 (C4 (Web Text))

Max Activating Token Index: 56

Text #15

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1217. Min Act: -0.0001

Data Index: 500910 (C4 (Web Text))

Max Activating Token Index: 662

Text #16

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1265. Min Act: -0.0001

Data Index: 607018 (C4 (Web Text))

Max Activating Token Index: 972

Text #17

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1238. Min Act: -0.0001

Data Index: 1091360 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1176. Min Act: -0.0001

Data Index: 508900 (C4 (Web Text))

Max Activating Token Index: 697

Text #19

Max Range: 0.1596. Min Range: -0.1596

Max Act: 0.1232. Min Act: -0.0001

Data Index: 124945 (C4 (Web Text))

Max Activating Token Index: 426