Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 871 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0503. Min Act: -0.0004

Data Index: 60889 (C4 (Web Text))

Max Activating Token Index: 543

Text #1

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0428. Min Act: -0.0004

Data Index: 875642 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0389. Min Act: -0.0004

Data Index: 1152018 (C4 (Web Text))

Max Activating Token Index: 207

Text #3

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0374. Min Act: -0.0004

Data Index: 71320 (C4 (Web Text))

Max Activating Token Index: 904

Text #4

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0373. Min Act: -0.0004

Data Index: 1236541 (C4 (Web Text))

Max Activating Token Index: 743

Text #5

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0322. Min Act: -0.0004

Data Index: 690750 (C4 (Web Text))

Max Activating Token Index: 884

Text #6

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0385. Min Act: -0.0004

Data Index: 1107015 (C4 (Web Text))

Max Activating Token Index: 961

Text #7

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0384. Min Act: -0.0004

Data Index: 924392 (C4 (Web Text))

Max Activating Token Index: 192

Text #8

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0351. Min Act: -0.0004

Data Index: 1316854 (C4 (Web Text))

Max Activating Token Index: 274

Text #9

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0357. Min Act: -0.0004

Data Index: 586812 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0354. Min Act: -0.0004

Data Index: 1264545 (C4 (Web Text))

Max Activating Token Index: 219

Text #11

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0383. Min Act: -0.0004

Data Index: 622930 (C4 (Web Text))

Max Activating Token Index: 902

Text #12

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0352. Min Act: -0.0004

Data Index: 805030 (C4 (Web Text))

Max Activating Token Index: 829

Text #13

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0329. Min Act: -0.0004

Data Index: 81164 (C4 (Web Text))

Max Activating Token Index: 809

Text #14

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0368. Min Act: -0.0004

Data Index: 1072795 (C4 (Web Text))

Max Activating Token Index: 1002

Text #15

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0376. Min Act: -0.0004

Data Index: 218259 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0372. Min Act: -0.0004

Data Index: 432313 (C4 (Web Text))

Max Activating Token Index: 391

Text #17

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0353. Min Act: -0.0004

Data Index: 1092740 (C4 (Web Text))

Max Activating Token Index: 144

Text #18

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0312. Min Act: -0.0004

Data Index: 1213020 (C4 (Web Text))

Max Activating Token Index: 606

Text #19

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0348. Min Act: -0.0004

Data Index: 390635 (C4 (Web Text))

Max Activating Token Index: 969