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

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

Neuron 1844 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: 0.0384. Min Range: -0.0384

Max Act: 0.0384. Min Act: -0.0004

Data Index: 203794 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0362. Min Act: -0.0003

Data Index: 1298812 (C4 (Web Text))

Max Activating Token Index: 135

Text #2

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0368. Min Act: -0.0003

Data Index: 1110350 (C4 (Web Text))

Max Activating Token Index: 13

Text #3

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0344. Min Act: -0.0002

Data Index: 164042 (C4 (Web Text))

Max Activating Token Index: 876

Text #4

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0334. Min Act: -0.0004

Data Index: 437472 (C4 (Web Text))

Max Activating Token Index: 656

Text #5

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0333. Min Act: -0.0003

Data Index: 1135040 (C4 (Web Text))

Max Activating Token Index: 1017

Text #6

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0346. Min Act: -0.0003

Data Index: 195841 (C4 (Web Text))

Max Activating Token Index: 244

Text #7

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0318. Min Act: -0.0003

Data Index: 79114 (C4 (Web Text))

Max Activating Token Index: 685

Text #8

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0322. Min Act: -0.0004

Data Index: 702750 (C4 (Web Text))

Max Activating Token Index: 1022

Text #9

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0322. Min Act: -0.0003

Data Index: 267574 (C4 (Web Text))

Max Activating Token Index: 528

Text #10

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0321. Min Act: -0.0003

Data Index: 410550 (C4 (Web Text))

Max Activating Token Index: 663

Text #11

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0328. Min Act: -0.0004

Data Index: 1195072 (C4 (Web Text))

Max Activating Token Index: 385

Text #12

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0326. Min Act: -0.0003

Data Index: 611284 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0320. Min Act: -0.0003

Data Index: 937960 (C4 (Web Text))

Max Activating Token Index: 886

Text #14

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0309. Min Act: -0.0003

Data Index: 455339 (C4 (Web Text))

Max Activating Token Index: 606

Text #15

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0309. Min Act: -0.0002

Data Index: 1067630 (C4 (Web Text))

Max Activating Token Index: 430

Text #16

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0327. Min Act: -0.0003

Data Index: 20406 (C4 (Web Text))

Max Activating Token Index: 970

Text #17

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0307. Min Act: -0.0002

Data Index: 1144278 (C4 (Web Text))

Max Activating Token Index: 581

Text #18

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0312. Min Act: -0.0003

Data Index: 498772 (C4 (Web Text))

Max Activating Token Index: 499

Text #19

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0320. Min Act: -0.0003

Data Index: 949106 (C4 (Web Text))

Max Activating Token Index: 705