Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 806 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4156. Min Range: -0.4156

Max Act: 0.4156. Min Act: -0.0000

Data Index: 222330 (C4 (Web Text))

Max Activating Token Index: 845

Text #1

Max Range: 0.4156. Min Range: -0.4156

Max Act: 0.3598. Min Act: -0.0000

Data Index: 703628 (C4 (Web Text))

Max Activating Token Index: 299

Text #2

Max Range: 0.4156. Min Range: -0.4156

Max Act: 0.3906. Min Act: -0.0000

Data Index: 156376 (C4 (Web Text))

Max Activating Token Index: 632

Text #3

Max Range: 0.4156. Min Range: -0.4156

Max Act: 0.3458. Min Act: -0.0000

Data Index: 453654 (C4 (Web Text))

Max Activating Token Index: 368

Text #4

Max Range: 0.4156. Min Range: -0.4156

Max Act: 0.3551. Min Act: -0.0000

Data Index: 1608689 (Python Code)

Max Activating Token Index: 764

Text #5

Max Range: 0.4156. Min Range: -0.4156

Max Act: 0.3412. Min Act: -0.0000

Data Index: 263233 (C4 (Web Text))

Max Activating Token Index: 415

Text #6

Max Range: 0.4156. Min Range: -0.4156

Max Act: 0.3184. Min Act: -0.0000

Data Index: 157754 (C4 (Web Text))

Max Activating Token Index: 566

Text #7

Max Range: 0.4156. Min Range: -0.4156

Max Act: 0.3290. Min Act: -0.0000

Data Index: 591870 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 0.4156. Min Range: -0.4156

Max Act: 0.3258. Min Act: -0.0000

Data Index: 295028 (C4 (Web Text))

Max Activating Token Index: 537

Text #9

Max Range: 0.4156. Min Range: -0.4156

Max Act: 0.3035. Min Act: -0.0000

Data Index: 674457 (C4 (Web Text))

Max Activating Token Index: 559

Text #10

Max Range: 0.4156. Min Range: -0.4156

Max Act: 0.3259. Min Act: -0.0000

Data Index: 531558 (C4 (Web Text))

Max Activating Token Index: 685

Text #11

Max Range: 0.4156. Min Range: -0.4156

Max Act: 0.3000. Min Act: -0.0000

Data Index: 93562 (C4 (Web Text))

Max Activating Token Index: 268

Text #12

Max Range: 0.4156. Min Range: -0.4156

Max Act: 0.3208. Min Act: -0.0000

Data Index: 1239965 (C4 (Web Text))

Max Activating Token Index: 193

Text #13

Max Range: 0.4156. Min Range: -0.4156

Max Act: 0.2985. Min Act: 0.0000

Data Index: 500585 (C4 (Web Text))

Max Activating Token Index: 610

Text #14

Max Range: 0.4156. Min Range: -0.4156

Max Act: 0.2797. Min Act: 0.0000

Data Index: 538405 (C4 (Web Text))

Max Activating Token Index: 183

Text #15

Max Range: 0.4156. Min Range: -0.4156

Max Act: 0.2667. Min Act: -0.0000

Data Index: 3588 (C4 (Web Text))

Max Activating Token Index: 84

Text #16

Max Range: 0.4156. Min Range: -0.4156

Max Act: 0.2397. Min Act: -0.0000

Data Index: 509698 (C4 (Web Text))

Max Activating Token Index: 841

Text #17

Max Range: 0.4156. Min Range: -0.4156

Max Act: 0.2617. Min Act: -0.0000

Data Index: 627904 (C4 (Web Text))

Max Activating Token Index: 916

Text #18

Max Range: 0.4156. Min Range: -0.4156

Max Act: 0.2194. Min Act: 0.0000

Data Index: 914016 (C4 (Web Text))

Max Activating Token Index: 165

Text #19

Max Range: 0.4156. Min Range: -0.4156

Max Act: 0.2491. Min Act: -0.0000

Data Index: 1347425 (C4 (Web Text))

Max Activating Token Index: 253