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

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

Neuron 1920 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: 0.3153. Min Range: -0.3153

Max Act: 0.3153. Min Act: -0.0003

Data Index: 323785 (C4 (Web Text))

Max Activating Token Index: 365

Text #1

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.3087. Min Act: -0.0003

Data Index: 44403 (C4 (Web Text))

Max Activating Token Index: 606

Text #2

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.3117. Min Act: -0.0003

Data Index: 383213 (C4 (Web Text))

Max Activating Token Index: 285

Text #3

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2928. Min Act: -0.0002

Data Index: 558209 (C4 (Web Text))

Max Activating Token Index: 55

Text #4

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2977. Min Act: -0.0003

Data Index: 1309273 (C4 (Web Text))

Max Activating Token Index: 678

Text #5

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.3005. Min Act: -0.0002

Data Index: 1216834 (C4 (Web Text))

Max Activating Token Index: 326

Text #6

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2661. Min Act: -0.0003

Data Index: 224290 (C4 (Web Text))

Max Activating Token Index: 1003

Text #7

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2828. Min Act: -0.0002

Data Index: 368933 (C4 (Web Text))

Max Activating Token Index: 311

Text #8

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2639. Min Act: -0.0002

Data Index: 912271 (C4 (Web Text))

Max Activating Token Index: 514

Text #9

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2736. Min Act: -0.0004

Data Index: 931992 (C4 (Web Text))

Max Activating Token Index: 439

Text #10

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2612. Min Act: -0.0003

Data Index: 1204393 (C4 (Web Text))

Max Activating Token Index: 180

Text #11

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2544. Min Act: -0.0002

Data Index: 710437 (C4 (Web Text))

Max Activating Token Index: 202

Text #12

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2531. Min Act: -0.0003

Data Index: 217159 (C4 (Web Text))

Max Activating Token Index: 353

Text #13

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2537. Min Act: -0.0003

Data Index: 318474 (C4 (Web Text))

Max Activating Token Index: 21

Text #14

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2546. Min Act: -0.0003

Data Index: 654573 (C4 (Web Text))

Max Activating Token Index: 707

Text #15

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2528. Min Act: -0.0003

Data Index: 295072 (C4 (Web Text))

Max Activating Token Index: 553

Text #16

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2405. Min Act: -0.0001

Data Index: 1345140 (C4 (Web Text))

Max Activating Token Index: 939

Text #17

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2373. Min Act: -0.0004

Data Index: 1336287 (C4 (Web Text))

Max Activating Token Index: 71

Text #18

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2363. Min Act: -0.0002

Data Index: 602519 (C4 (Web Text))

Max Activating Token Index: 920

Text #19

Max Range: 0.3153. Min Range: -0.3153

Max Act: 0.2432. Min Act: -0.0002

Data Index: 1169599 (C4 (Web Text))

Max Activating Token Index: 169