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

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

Neuron 1521 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0426. Min Act: -0.0002

Data Index: 983767 (C4 (Web Text))

Max Activating Token Index: 51

Text #1

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0430. Min Act: -0.0001

Data Index: 690855 (C4 (Web Text))

Max Activating Token Index: 270

Text #2

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0368. Min Act: -0.0001

Data Index: 906338 (C4 (Web Text))

Max Activating Token Index: 223

Text #3

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0370. Min Act: -0.0001

Data Index: 1151248 (C4 (Web Text))

Max Activating Token Index: 726

Text #4

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0395. Min Act: -0.0002

Data Index: 487465 (C4 (Web Text))

Max Activating Token Index: 822

Text #5

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0351. Min Act: -0.0002

Data Index: 1344853 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0347. Min Act: -0.0001

Data Index: 1356851 (C4 (Web Text))

Max Activating Token Index: 438

Text #7

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0388. Min Act: -0.0001

Data Index: 749092 (C4 (Web Text))

Max Activating Token Index: 145

Text #8

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0358. Min Act: -0.0001

Data Index: 828152 (C4 (Web Text))

Max Activating Token Index: 443

Text #9

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0369. Min Act: -0.0002

Data Index: 55188 (C4 (Web Text))

Max Activating Token Index: 685

Text #10

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0321. Min Act: -0.0001

Data Index: 1321459 (C4 (Web Text))

Max Activating Token Index: 538

Text #11

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0322. Min Act: -0.0002

Data Index: 346684 (C4 (Web Text))

Max Activating Token Index: 134

Text #12

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0328. Min Act: -0.0002

Data Index: 276431 (C4 (Web Text))

Max Activating Token Index: 136

Text #13

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0330. Min Act: -0.0001

Data Index: 893816 (C4 (Web Text))

Max Activating Token Index: 465

Text #14

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0313. Min Act: -0.0001

Data Index: 464357 (C4 (Web Text))

Max Activating Token Index: 329

Text #15

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0332. Min Act: -0.0001

Data Index: 800842 (C4 (Web Text))

Max Activating Token Index: 87

Text #16

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0325. Min Act: -0.0002

Data Index: 383990 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0312. Min Act: -0.0001

Data Index: 988969 (C4 (Web Text))

Max Activating Token Index: 775

Text #18

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0322. Min Act: -0.0001

Data Index: 646432 (C4 (Web Text))

Max Activating Token Index: 165

Text #19

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0316. Min Act: -0.0001

Data Index: 415710 (C4 (Web Text))

Max Activating Token Index: 211