Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 309 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0486. Min Act: -0.0003

Data Index: 440533 (C4 (Web Text))

Max Activating Token Index: 391

Text #1

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0382. Min Act: -0.0003

Data Index: 972355 (C4 (Web Text))

Max Activating Token Index: 971

Text #2

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0379. Min Act: -0.0003

Data Index: 362249 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0356. Min Act: -0.0003

Data Index: 1231522 (C4 (Web Text))

Max Activating Token Index: 838

Text #4

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0355. Min Act: -0.0003

Data Index: 1078212 (C4 (Web Text))

Max Activating Token Index: 926

Text #5

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0358. Min Act: -0.0003

Data Index: 531621 (C4 (Web Text))

Max Activating Token Index: 462

Text #6

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0354. Min Act: -0.0003

Data Index: 1286080 (C4 (Web Text))

Max Activating Token Index: 710

Text #7

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0358. Min Act: -0.0003

Data Index: 977581 (C4 (Web Text))

Max Activating Token Index: 987

Text #8

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0366. Min Act: -0.0003

Data Index: 551959 (C4 (Web Text))

Max Activating Token Index: 865

Text #9

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0320. Min Act: -0.0003

Data Index: 1310664 (C4 (Web Text))

Max Activating Token Index: 876

Text #10

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0384. Min Act: -0.0004

Data Index: 1316305 (C4 (Web Text))

Max Activating Token Index: 522

Text #11

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0346. Min Act: -0.0003

Data Index: 329234 (C4 (Web Text))

Max Activating Token Index: 318

Text #12

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0347. Min Act: -0.0003

Data Index: 41391 (C4 (Web Text))

Max Activating Token Index: 917

Text #13

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0321. Min Act: -0.0003

Data Index: 601975 (C4 (Web Text))

Max Activating Token Index: 568

Text #14

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0347. Min Act: -0.0003

Data Index: 1079780 (C4 (Web Text))

Max Activating Token Index: 481

Text #15

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0342. Min Act: -0.0002

Data Index: 1339190 (C4 (Web Text))

Max Activating Token Index: 105

Text #16

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0323. Min Act: -0.0002

Data Index: 1060573 (C4 (Web Text))

Max Activating Token Index: 1004

Text #17

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0329. Min Act: -0.0003

Data Index: 236103 (C4 (Web Text))

Max Activating Token Index: 973

Text #18

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0337. Min Act: -0.0003

Data Index: 652150 (C4 (Web Text))

Max Activating Token Index: 389

Text #19

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0330. Min Act: -0.0003

Data Index: 1239610 (C4 (Web Text))

Max Activating Token Index: 90