Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1300 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.4225. Min Act: -0.0000

Data Index: 799145 (C4 (Web Text))

Max Activating Token Index: 543

Text #1

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3507. Min Act: -0.0000

Data Index: 583991 (C4 (Web Text))

Max Activating Token Index: 329

Text #2

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3565. Min Act: -0.0000

Data Index: 186101 (C4 (Web Text))

Max Activating Token Index: 435

Text #3

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.2804. Min Act: -0.0000

Data Index: 545764 (C4 (Web Text))

Max Activating Token Index: 889

Text #4

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3199. Min Act: -0.0000

Data Index: 401901 (C4 (Web Text))

Max Activating Token Index: 63

Text #5

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.2924. Min Act: -0.0000

Data Index: 343088 (C4 (Web Text))

Max Activating Token Index: 71

Text #6

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3345. Min Act: -0.0000

Data Index: 933793 (C4 (Web Text))

Max Activating Token Index: 998

Text #7

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3078. Min Act: -0.0000

Data Index: 230784 (C4 (Web Text))

Max Activating Token Index: 540

Text #8

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.2864. Min Act: -0.0000

Data Index: 979449 (C4 (Web Text))

Max Activating Token Index: 920

Text #9

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3094. Min Act: -0.0000

Data Index: 1144565 (C4 (Web Text))

Max Activating Token Index: 353

Text #10

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.2747. Min Act: -0.0000

Data Index: 1235900 (C4 (Web Text))

Max Activating Token Index: 647

Text #11

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.2501. Min Act: -0.0000

Data Index: 811210 (C4 (Web Text))

Max Activating Token Index: 271

Text #12

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.2457. Min Act: -0.0000

Data Index: 1297598 (C4 (Web Text))

Max Activating Token Index: 790

Text #13

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.2244. Min Act: -0.0000

Data Index: 967514 (C4 (Web Text))

Max Activating Token Index: 149

Text #14

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.2467. Min Act: -0.0000

Data Index: 34354 (C4 (Web Text))

Max Activating Token Index: 251

Text #15

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.2445. Min Act: -0.0000

Data Index: 357354 (C4 (Web Text))

Max Activating Token Index: 432

Text #16

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.2235. Min Act: 0.0001

Data Index: 275666 (C4 (Web Text))

Max Activating Token Index: 156

Text #17

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.2421. Min Act: -0.0000

Data Index: 1194340 (C4 (Web Text))

Max Activating Token Index: 844

Text #18

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.2175. Min Act: -0.0000

Data Index: 715285 (C4 (Web Text))

Max Activating Token Index: 72

Text #19

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.2111. Min Act: -0.0000

Data Index: 204797 (C4 (Web Text))

Max Activating Token Index: 838