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

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

Neuron 1638 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0422. Min Act: -0.0006

Data Index: 363065 (C4 (Web Text))

Max Activating Token Index: 1001

Text #1

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0414. Min Act: -0.0006

Data Index: 363126 (C4 (Web Text))

Max Activating Token Index: 396

Text #2

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0377. Min Act: -0.0006

Data Index: 1168183 (C4 (Web Text))

Max Activating Token Index: 756

Text #3

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0367. Min Act: -0.0006

Data Index: 531481 (C4 (Web Text))

Max Activating Token Index: 425

Text #4

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0372. Min Act: -0.0006

Data Index: 547444 (C4 (Web Text))

Max Activating Token Index: 572

Text #5

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0376. Min Act: -0.0006

Data Index: 1189934 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0375. Min Act: -0.0006

Data Index: 407607 (C4 (Web Text))

Max Activating Token Index: 365

Text #7

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0368. Min Act: -0.0006

Data Index: 1067619 (C4 (Web Text))

Max Activating Token Index: 329

Text #8

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0378. Min Act: -0.0006

Data Index: 876692 (C4 (Web Text))

Max Activating Token Index: 926

Text #9

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0373. Min Act: -0.0006

Data Index: 1284268 (C4 (Web Text))

Max Activating Token Index: 634

Text #10

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0363. Min Act: -0.0006

Data Index: 949655 (C4 (Web Text))

Max Activating Token Index: 599

Text #11

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0340. Min Act: -0.0006

Data Index: 677455 (C4 (Web Text))

Max Activating Token Index: 773

Text #12

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0361. Min Act: -0.0005

Data Index: 174563 (C4 (Web Text))

Max Activating Token Index: 499

Text #13

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0351. Min Act: -0.0006

Data Index: 58759 (C4 (Web Text))

Max Activating Token Index: 685

Text #14

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0357. Min Act: -0.0006

Data Index: 199471 (C4 (Web Text))

Max Activating Token Index: 672

Text #15

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0346. Min Act: -0.0005

Data Index: 706860 (C4 (Web Text))

Max Activating Token Index: 24

Text #16

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0330. Min Act: -0.0005

Data Index: 988260 (C4 (Web Text))

Max Activating Token Index: 756

Text #17

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0352. Min Act: -0.0006

Data Index: 418447 (C4 (Web Text))

Max Activating Token Index: 945

Text #18

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0343. Min Act: -0.0005

Data Index: 266537 (C4 (Web Text))

Max Activating Token Index: 805

Text #19

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0358. Min Act: -0.0006

Data Index: 1288489 (C4 (Web Text))

Max Activating Token Index: 638