Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4928 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.6281. Min Act: -0.0000

Data Index: 558011 (C4 (Web Text))

Max Activating Token Index: 720

Text #1

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.5625. Min Act: -0.0000

Data Index: 945612 (C4 (Web Text))

Max Activating Token Index: 261

Text #2

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.5693. Min Act: -0.0000

Data Index: 984321 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.5401. Min Act: -0.0000

Data Index: 193584 (C4 (Web Text))

Max Activating Token Index: 569

Text #4

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.5249. Min Act: -0.0000

Data Index: 5596 (C4 (Web Text))

Max Activating Token Index: 552

Text #5

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.5051. Min Act: -0.0000

Data Index: 646783 (C4 (Web Text))

Max Activating Token Index: 993

Text #6

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.4893. Min Act: -0.0000

Data Index: 859835 (C4 (Web Text))

Max Activating Token Index: 675

Text #7

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.4492. Min Act: -0.0000

Data Index: 1140835 (C4 (Web Text))

Max Activating Token Index: 517

Text #8

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.4553. Min Act: -0.0000

Data Index: 422653 (C4 (Web Text))

Max Activating Token Index: 908

Text #9

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.4520. Min Act: -0.0000

Data Index: 326481 (C4 (Web Text))

Max Activating Token Index: 639

Text #10

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.4370. Min Act: -0.0000

Data Index: 1032749 (C4 (Web Text))

Max Activating Token Index: 100

Text #11

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.4148. Min Act: -0.0000

Data Index: 266287 (C4 (Web Text))

Max Activating Token Index: 1004

Text #12

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.4222. Min Act: -0.0000

Data Index: 469331 (C4 (Web Text))

Max Activating Token Index: 859

Text #13

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.4358. Min Act: -0.0000

Data Index: 1246285 (C4 (Web Text))

Max Activating Token Index: 609

Text #14

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.4361. Min Act: -0.0000

Data Index: 885209 (C4 (Web Text))

Max Activating Token Index: 136

Text #15

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.4196. Min Act: -0.0000

Data Index: 1039322 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.3962. Min Act: -0.0000

Data Index: 1350451 (C4 (Web Text))

Max Activating Token Index: 781

Text #17

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.4050. Min Act: -0.0000

Data Index: 323627 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.4146. Min Act: -0.0000

Data Index: 1181963 (C4 (Web Text))

Max Activating Token Index: 670

Text #19

Max Range: 0.6281. Min Range: -0.6281

Max Act: 0.3870. Min Act: -0.0000

Data Index: 52263 (C4 (Web Text))

Max Activating Token Index: 579