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

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

Neuron 3073 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: 1.8339. Min Range: -1.8339

Max Act: 1.8339. Min Act: -0.0000

Data Index: 1258913 (C4 (Web Text))

Max Activating Token Index: 68

Text #1

Max Range: 1.8339. Min Range: -1.8339

Max Act: 1.4049. Min Act: -0.0001

Data Index: 181807 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 1.8339. Min Range: -1.8339

Max Act: 1.0997. Min Act: -0.0000

Data Index: 1266081 (C4 (Web Text))

Max Activating Token Index: 88

Text #3

Max Range: 1.8339. Min Range: -1.8339

Max Act: 0.9619. Min Act: -0.0001

Data Index: 1333419 (C4 (Web Text))

Max Activating Token Index: 1009

Text #4

Max Range: 1.8339. Min Range: -1.8339

Max Act: 0.9386. Min Act: -0.0000

Data Index: 652791 (C4 (Web Text))

Max Activating Token Index: 718

Text #5

Max Range: 1.8339. Min Range: -1.8339

Max Act: 0.8468. Min Act: -0.0000

Data Index: 25853 (C4 (Web Text))

Max Activating Token Index: 124

Text #6

Max Range: 1.8339. Min Range: -1.8339

Max Act: 0.7976. Min Act: -0.0001

Data Index: 287135 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 1.8339. Min Range: -1.8339

Max Act: 0.8418. Min Act: -0.0000

Data Index: 1256377 (C4 (Web Text))

Max Activating Token Index: 308

Text #8

Max Range: 1.8339. Min Range: -1.8339

Max Act: 0.8370. Min Act: -0.0000

Data Index: 689538 (C4 (Web Text))

Max Activating Token Index: 182

Text #9

Max Range: 1.8339. Min Range: -1.8339

Max Act: 0.7417. Min Act: -0.0000

Data Index: 647666 (C4 (Web Text))

Max Activating Token Index: 550

Text #10

Max Range: 1.8339. Min Range: -1.8339

Max Act: 0.8917. Min Act: -0.0000

Data Index: 115198 (C4 (Web Text))

Max Activating Token Index: 771

Text #11

Max Range: 1.8339. Min Range: -1.8339

Max Act: 0.8382. Min Act: -0.0000

Data Index: 1129372 (C4 (Web Text))

Max Activating Token Index: 271

Text #12

Max Range: 1.8339. Min Range: -1.8339

Max Act: 0.7405. Min Act: -0.0000

Data Index: 553808 (C4 (Web Text))

Max Activating Token Index: 735

Text #13

Max Range: 1.8339. Min Range: -1.8339

Max Act: 0.8327. Min Act: -0.0000

Data Index: 1147227 (C4 (Web Text))

Max Activating Token Index: 438

Text #14

Max Range: 1.8339. Min Range: -1.8339

Max Act: 0.7882. Min Act: -0.0000

Data Index: 1157179 (C4 (Web Text))

Max Activating Token Index: 379

Text #15

Max Range: 1.8339. Min Range: -1.8339

Max Act: 0.7988. Min Act: -0.0000

Data Index: 166344 (C4 (Web Text))

Max Activating Token Index: 280

Text #16

Max Range: 1.8339. Min Range: -1.8339

Max Act: 0.8348. Min Act: -0.0000

Data Index: 794763 (C4 (Web Text))

Max Activating Token Index: 607

Text #17

Max Range: 1.8339. Min Range: -1.8339

Max Act: 0.7876. Min Act: -0.0000

Data Index: 272100 (C4 (Web Text))

Max Activating Token Index: 668

Text #18

Max Range: 1.8339. Min Range: -1.8339

Max Act: 0.7679. Min Act: -0.0000

Data Index: 636320 (C4 (Web Text))

Max Activating Token Index: 780

Text #19

Max Range: 1.8339. Min Range: -1.8339

Max Act: 0.8231. Min Act: -0.0001

Data Index: 306365 (C4 (Web Text))

Max Activating Token Index: 931