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

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

Neuron 67 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: 0.0434. Min Range: -0.0434

Max Act: 0.0434. Min Act: -0.0003

Data Index: 418608 (C4 (Web Text))

Max Activating Token Index: 756

Text #1

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0397. Min Act: -0.0003

Data Index: 962799 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0397. Min Act: -0.0003

Data Index: 103504 (C4 (Web Text))

Max Activating Token Index: 1021

Text #3

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0387. Min Act: -0.0003

Data Index: 772039 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0376. Min Act: -0.0003

Data Index: 758738 (C4 (Web Text))

Max Activating Token Index: 501

Text #5

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0364. Min Act: -0.0003

Data Index: 530093 (C4 (Web Text))

Max Activating Token Index: 388

Text #6

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0385. Min Act: -0.0003

Data Index: 424689 (C4 (Web Text))

Max Activating Token Index: 433

Text #7

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0355. Min Act: -0.0002

Data Index: 171956 (C4 (Web Text))

Max Activating Token Index: 926

Text #8

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0350. Min Act: -0.0003

Data Index: 142966 (C4 (Web Text))

Max Activating Token Index: 596

Text #9

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0355. Min Act: -0.0003

Data Index: 2214 (C4 (Web Text))

Max Activating Token Index: 745

Text #10

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0349. Min Act: -0.0003

Data Index: 930002 (C4 (Web Text))

Max Activating Token Index: 334

Text #11

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0347. Min Act: -0.0003

Data Index: 1173893 (C4 (Web Text))

Max Activating Token Index: 888

Text #12

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0344. Min Act: -0.0003

Data Index: 379922 (C4 (Web Text))

Max Activating Token Index: 711

Text #13

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0328. Min Act: -0.0003

Data Index: 897261 (C4 (Web Text))

Max Activating Token Index: 761

Text #14

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0346. Min Act: -0.0003

Data Index: 835455 (C4 (Web Text))

Max Activating Token Index: 423

Text #15

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0338. Min Act: -0.0002

Data Index: 403199 (C4 (Web Text))

Max Activating Token Index: 773

Text #16

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0319. Min Act: -0.0004

Data Index: 528945 (C4 (Web Text))

Max Activating Token Index: 176

Text #17

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0343. Min Act: -0.0003

Data Index: 662830 (C4 (Web Text))

Max Activating Token Index: 660

Text #18

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0336. Min Act: -0.0003

Data Index: 1114562 (C4 (Web Text))

Max Activating Token Index: 186

Text #19

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0325. Min Act: -0.0003

Data Index: 1247015 (C4 (Web Text))

Max Activating Token Index: 277