Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 709 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0448. Min Act: -0.0005

Data Index: 965514 (C4 (Web Text))

Max Activating Token Index: 786

Text #1

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0414. Min Act: -0.0005

Data Index: 281725 (C4 (Web Text))

Max Activating Token Index: 359

Text #2

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0418. Min Act: -0.0005

Data Index: 488396 (C4 (Web Text))

Max Activating Token Index: 230

Text #3

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0440. Min Act: -0.0005

Data Index: 693524 (C4 (Web Text))

Max Activating Token Index: 308

Text #4

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0407. Min Act: -0.0005

Data Index: 669335 (C4 (Web Text))

Max Activating Token Index: 330

Text #5

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0401. Min Act: -0.0005

Data Index: 1146327 (C4 (Web Text))

Max Activating Token Index: 630

Text #6

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0375. Min Act: -0.0005

Data Index: 673293 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0371. Min Act: -0.0005

Data Index: 1195665 (C4 (Web Text))

Max Activating Token Index: 1006

Text #8

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0383. Min Act: -0.0005

Data Index: 927813 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0389. Min Act: -0.0005

Data Index: 663894 (C4 (Web Text))

Max Activating Token Index: 488

Text #10

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0381. Min Act: -0.0005

Data Index: 564025 (C4 (Web Text))

Max Activating Token Index: 421

Text #11

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0400. Min Act: -0.0005

Data Index: 861601 (C4 (Web Text))

Max Activating Token Index: 254

Text #12

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0393. Min Act: -0.0005

Data Index: 460767 (C4 (Web Text))

Max Activating Token Index: 249

Text #13

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0368. Min Act: -0.0005

Data Index: 245663 (C4 (Web Text))

Max Activating Token Index: 811

Text #14

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0352. Min Act: -0.0005

Data Index: 1344866 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0349. Min Act: -0.0005

Data Index: 939343 (C4 (Web Text))

Max Activating Token Index: 238

Text #16

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0345. Min Act: -0.0005

Data Index: 817132 (C4 (Web Text))

Max Activating Token Index: 730

Text #17

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0340. Min Act: -0.0005

Data Index: 89981 (C4 (Web Text))

Max Activating Token Index: 913

Text #18

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0355. Min Act: -0.0005

Data Index: 734133 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0376. Min Act: -0.0005

Data Index: 811316 (C4 (Web Text))

Max Activating Token Index: 982