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

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

Neuron 912 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: 0.0418. Min Range: -0.0418

Max Act: 0.0418. Min Act: -0.0006

Data Index: 111133 (C4 (Web Text))

Max Activating Token Index: 871

Text #1

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0408. Min Act: -0.0006

Data Index: 574144 (C4 (Web Text))

Max Activating Token Index: 641

Text #2

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0391. Min Act: -0.0006

Data Index: 1117952 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0368. Min Act: -0.0006

Data Index: 887163 (C4 (Web Text))

Max Activating Token Index: 485

Text #4

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0371. Min Act: -0.0006

Data Index: 959215 (C4 (Web Text))

Max Activating Token Index: 832

Text #5

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0358. Min Act: -0.0006

Data Index: 1175058 (C4 (Web Text))

Max Activating Token Index: 470

Text #6

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0354. Min Act: -0.0006

Data Index: 131381 (C4 (Web Text))

Max Activating Token Index: 198

Text #7

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0365. Min Act: -0.0006

Data Index: 18047 (C4 (Web Text))

Max Activating Token Index: 557

Text #8

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0337. Min Act: -0.0006

Data Index: 585479 (C4 (Web Text))

Max Activating Token Index: 792

Text #9

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0341. Min Act: -0.0006

Data Index: 481067 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0320. Min Act: -0.0006

Data Index: 121490 (C4 (Web Text))

Max Activating Token Index: 727

Text #11

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0345. Min Act: -0.0006

Data Index: 283070 (C4 (Web Text))

Max Activating Token Index: 222

Text #12

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0338. Min Act: -0.0006

Data Index: 15209 (C4 (Web Text))

Max Activating Token Index: 440

Text #13

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0338. Min Act: -0.0006

Data Index: 689694 (C4 (Web Text))

Max Activating Token Index: 579

Text #14

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0334. Min Act: -0.0006

Data Index: 1056198 (C4 (Web Text))

Max Activating Token Index: 6

Text #15

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0340. Min Act: -0.0006

Data Index: 828959 (C4 (Web Text))

Max Activating Token Index: 519

Text #16

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0354. Min Act: -0.0006

Data Index: 1431495 (Python Code)

Max Activating Token Index: 637

Text #17

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0339. Min Act: -0.0006

Data Index: 337667 (C4 (Web Text))

Max Activating Token Index: 370

Text #18

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0325. Min Act: -0.0006

Data Index: 1588453 (Python Code)

Max Activating Token Index: 846

Text #19

Max Range: 0.0418. Min Range: -0.0418

Max Act: 0.0337. Min Act: -0.0006

Data Index: 36430 (C4 (Web Text))

Max Activating Token Index: 5