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

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

Neuron 2303 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: 0.0472. Min Range: -0.0472

Max Act: 0.0469. Min Act: -0.0004

Data Index: 1281984 (C4 (Web Text))

Max Activating Token Index: 471

Text #1

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0472. Min Act: -0.0004

Data Index: 73050 (C4 (Web Text))

Max Activating Token Index: 257

Text #2

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0384. Min Act: -0.0004

Data Index: 287642 (C4 (Web Text))

Max Activating Token Index: 569

Text #3

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0395. Min Act: -0.0004

Data Index: 792750 (C4 (Web Text))

Max Activating Token Index: 673

Text #4

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0356. Min Act: -0.0004

Data Index: 323404 (C4 (Web Text))

Max Activating Token Index: 266

Text #5

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0331. Min Act: -0.0004

Data Index: 194594 (C4 (Web Text))

Max Activating Token Index: 543

Text #6

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0325. Min Act: -0.0004

Data Index: 624010 (C4 (Web Text))

Max Activating Token Index: 342

Text #7

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0382. Min Act: -0.0004

Data Index: 865765 (C4 (Web Text))

Max Activating Token Index: 315

Text #8

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0356. Min Act: -0.0004

Data Index: 1312134 (C4 (Web Text))

Max Activating Token Index: 395

Text #9

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0417. Min Act: -0.0004

Data Index: 1355399 (C4 (Web Text))

Max Activating Token Index: 392

Text #10

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0300. Min Act: -0.0004

Data Index: 344893 (C4 (Web Text))

Max Activating Token Index: 612

Text #11

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0357. Min Act: -0.0004

Data Index: 1068146 (C4 (Web Text))

Max Activating Token Index: 795

Text #12

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0365. Min Act: -0.0004

Data Index: 710832 (C4 (Web Text))

Max Activating Token Index: 419

Text #13

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0335. Min Act: -0.0004

Data Index: 1134677 (C4 (Web Text))

Max Activating Token Index: 989

Text #14

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0370. Min Act: -0.0004

Data Index: 27710 (C4 (Web Text))

Max Activating Token Index: 66

Text #15

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0354. Min Act: -0.0004

Data Index: 408603 (C4 (Web Text))

Max Activating Token Index: 999

Text #16

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0363. Min Act: -0.0004

Data Index: 459690 (C4 (Web Text))

Max Activating Token Index: 949

Text #17

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0310. Min Act: -0.0004

Data Index: 436473 (C4 (Web Text))

Max Activating Token Index: 255

Text #18

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0344. Min Act: -0.0004

Data Index: 45307 (C4 (Web Text))

Max Activating Token Index: 616

Text #19

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0321. Min Act: -0.0004

Data Index: 1293793 (C4 (Web Text))

Max Activating Token Index: 372