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

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

Neuron 1309 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2678. Min Range: -0.2678

Max Act: 0.2602. Min Act: -0.0002

Data Index: 576300 (C4 (Web Text))

Max Activating Token Index: 280

Text #1

Max Range: 0.2678. Min Range: -0.2678

Max Act: 0.2678. Min Act: -0.0002

Data Index: 1357420 (C4 (Web Text))

Max Activating Token Index: 407

Text #2

Max Range: 0.2678. Min Range: -0.2678

Max Act: 0.2594. Min Act: -0.0002

Data Index: 578874 (C4 (Web Text))

Max Activating Token Index: 668

Text #3

Max Range: 0.2678. Min Range: -0.2678

Max Act: 0.2582. Min Act: -0.0002

Data Index: 1138943 (C4 (Web Text))

Max Activating Token Index: 517

Text #4

Max Range: 0.2678. Min Range: -0.2678

Max Act: 0.2488. Min Act: -0.0002

Data Index: 546434 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 0.2678. Min Range: -0.2678

Max Act: 0.2477. Min Act: -0.0002

Data Index: 267181 (C4 (Web Text))

Max Activating Token Index: 565

Text #6

Max Range: 0.2678. Min Range: -0.2678

Max Act: 0.2545. Min Act: -0.0002

Data Index: 257265 (C4 (Web Text))

Max Activating Token Index: 200

Text #7

Max Range: 0.2678. Min Range: -0.2678

Max Act: 0.2539. Min Act: -0.0002

Data Index: 1034228 (C4 (Web Text))

Max Activating Token Index: 324

Text #8

Max Range: 0.2678. Min Range: -0.2678

Max Act: 0.2450. Min Act: -0.0002

Data Index: 803844 (C4 (Web Text))

Max Activating Token Index: 605

Text #9

Max Range: 0.2678. Min Range: -0.2678

Max Act: 0.2389. Min Act: -0.0002

Data Index: 188631 (C4 (Web Text))

Max Activating Token Index: 727

Text #10

Max Range: 0.2678. Min Range: -0.2678

Max Act: 0.2443. Min Act: -0.0002

Data Index: 1228319 (C4 (Web Text))

Max Activating Token Index: 427

Text #11

Max Range: 0.2678. Min Range: -0.2678

Max Act: 0.2361. Min Act: -0.0002

Data Index: 1104041 (C4 (Web Text))

Max Activating Token Index: 186

Text #12

Max Range: 0.2678. Min Range: -0.2678

Max Act: 0.2434. Min Act: -0.0002

Data Index: 859593 (C4 (Web Text))

Max Activating Token Index: 503

Text #13

Max Range: 0.2678. Min Range: -0.2678

Max Act: 0.2413. Min Act: -0.0002

Data Index: 1202309 (C4 (Web Text))

Max Activating Token Index: 157

Text #14

Max Range: 0.2678. Min Range: -0.2678

Max Act: 0.2261. Min Act: -0.0002

Data Index: 40997 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 0.2678. Min Range: -0.2678

Max Act: 0.2333. Min Act: -0.0002

Data Index: 274396 (C4 (Web Text))

Max Activating Token Index: 342

Text #16

Max Range: 0.2678. Min Range: -0.2678

Max Act: 0.2387. Min Act: -0.0002

Data Index: 516751 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 0.2678. Min Range: -0.2678

Max Act: 0.2299. Min Act: -0.0002

Data Index: 108837 (C4 (Web Text))

Max Activating Token Index: 54

Text #18

Max Range: 0.2678. Min Range: -0.2678

Max Act: 0.2287. Min Act: -0.0002

Data Index: 1000992 (C4 (Web Text))

Max Activating Token Index: 570

Text #19

Max Range: 0.2678. Min Range: -0.2678

Max Act: 0.2360. Min Act: -0.0002

Data Index: 167456 (C4 (Web Text))

Max Activating Token Index: 371