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

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

Neuron 1888 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: 0.0472. Min Range: -0.0472

Max Act: 0.0472. Min Act: -0.0006

Data Index: 252833 (C4 (Web Text))

Max Activating Token Index: 796

Text #1

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0444. Min Act: -0.0006

Data Index: 181217 (C4 (Web Text))

Max Activating Token Index: 759

Text #2

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0435. Min Act: -0.0006

Data Index: 26190 (C4 (Web Text))

Max Activating Token Index: 648

Text #3

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0402. Min Act: -0.0006

Data Index: 479612 (C4 (Web Text))

Max Activating Token Index: 945

Text #4

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0391. Min Act: -0.0006

Data Index: 720897 (C4 (Web Text))

Max Activating Token Index: 586

Text #5

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0388. Min Act: -0.0006

Data Index: 171181 (C4 (Web Text))

Max Activating Token Index: 447

Text #6

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0377. Min Act: -0.0006

Data Index: 226406 (C4 (Web Text))

Max Activating Token Index: 806

Text #7

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0360. Min Act: -0.0006

Data Index: 682116 (C4 (Web Text))

Max Activating Token Index: 619

Text #8

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0382. Min Act: -0.0006

Data Index: 1125526 (C4 (Web Text))

Max Activating Token Index: 149

Text #9

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0377. Min Act: -0.0006

Data Index: 675782 (C4 (Web Text))

Max Activating Token Index: 127

Text #10

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0360. Min Act: -0.0006

Data Index: 797709 (C4 (Web Text))

Max Activating Token Index: 700

Text #11

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0366. Min Act: -0.0006

Data Index: 331058 (C4 (Web Text))

Max Activating Token Index: 403

Text #12

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0365. Min Act: -0.0006

Data Index: 1177174 (C4 (Web Text))

Max Activating Token Index: 649

Text #13

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0368. Min Act: -0.0006

Data Index: 1389536 (Python Code)

Max Activating Token Index: 48

Text #14

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0349. Min Act: -0.0006

Data Index: 949336 (C4 (Web Text))

Max Activating Token Index: 594

Text #15

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0325. Min Act: -0.0006

Data Index: 257624 (C4 (Web Text))

Max Activating Token Index: 227

Text #16

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0338. Min Act: -0.0006

Data Index: 869511 (C4 (Web Text))

Max Activating Token Index: 795

Text #17

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0337. Min Act: -0.0006

Data Index: 753256 (C4 (Web Text))

Max Activating Token Index: 270

Text #18

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0357. Min Act: -0.0006

Data Index: 495703 (C4 (Web Text))

Max Activating Token Index: 190

Text #19

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0341. Min Act: -0.0006

Data Index: 1456765 (Python Code)

Max Activating Token Index: 400