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

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

Neuron 14 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2858. Min Range: -0.2858

Max Act: 0.2858. Min Act: -0.0000

Data Index: 84028 (C4 (Web Text))

Max Activating Token Index: 802

Text #1

Max Range: 0.2858. Min Range: -0.2858

Max Act: 0.2777. Min Act: -0.0001

Data Index: 903778 (C4 (Web Text))

Max Activating Token Index: 891

Text #2

Max Range: 0.2858. Min Range: -0.2858

Max Act: 0.2838. Min Act: -0.0001

Data Index: 705562 (C4 (Web Text))

Max Activating Token Index: 502

Text #3

Max Range: 0.2858. Min Range: -0.2858

Max Act: 0.2516. Min Act: -0.0000

Data Index: 42058 (C4 (Web Text))

Max Activating Token Index: 278

Text #4

Max Range: 0.2858. Min Range: -0.2858

Max Act: 0.2712. Min Act: -0.0001

Data Index: 1018398 (C4 (Web Text))

Max Activating Token Index: 919

Text #5

Max Range: 0.2858. Min Range: -0.2858

Max Act: 0.2575. Min Act: -0.0000

Data Index: 201351 (C4 (Web Text))

Max Activating Token Index: 181

Text #6

Max Range: 0.2858. Min Range: -0.2858

Max Act: 0.2732. Min Act: -0.0000

Data Index: 504365 (C4 (Web Text))

Max Activating Token Index: 418

Text #7

Max Range: 0.2858. Min Range: -0.2858

Max Act: 0.2515. Min Act: -0.0001

Data Index: 695747 (C4 (Web Text))

Max Activating Token Index: 162

Text #8

Max Range: 0.2858. Min Range: -0.2858

Max Act: 0.2492. Min Act: -0.0001

Data Index: 52125 (C4 (Web Text))

Max Activating Token Index: 700

Text #9

Max Range: 0.2858. Min Range: -0.2858

Max Act: 0.2548. Min Act: -0.0001

Data Index: 846948 (C4 (Web Text))

Max Activating Token Index: 329

Text #10

Max Range: 0.2858. Min Range: -0.2858

Max Act: 0.2502. Min Act: -0.0000

Data Index: 1091734 (C4 (Web Text))

Max Activating Token Index: 873

Text #11

Max Range: 0.2858. Min Range: -0.2858

Max Act: 0.2593. Min Act: -0.0001

Data Index: 10816 (C4 (Web Text))

Max Activating Token Index: 813

Text #12

Max Range: 0.2858. Min Range: -0.2858

Max Act: 0.2578. Min Act: -0.0001

Data Index: 401656 (C4 (Web Text))

Max Activating Token Index: 287

Text #13

Max Range: 0.2858. Min Range: -0.2858

Max Act: 0.2395. Min Act: -0.0000

Data Index: 747079 (C4 (Web Text))

Max Activating Token Index: 714

Text #14

Max Range: 0.2858. Min Range: -0.2858

Max Act: 0.2491. Min Act: -0.0000

Data Index: 873710 (C4 (Web Text))

Max Activating Token Index: 392

Text #15

Max Range: 0.2858. Min Range: -0.2858

Max Act: 0.2189. Min Act: -0.0001

Data Index: 564288 (C4 (Web Text))

Max Activating Token Index: 534

Text #16

Max Range: 0.2858. Min Range: -0.2858

Max Act: 0.2179. Min Act: -0.0000

Data Index: 308659 (C4 (Web Text))

Max Activating Token Index: 414

Text #17

Max Range: 0.2858. Min Range: -0.2858

Max Act: 0.2256. Min Act: -0.0000

Data Index: 954067 (C4 (Web Text))

Max Activating Token Index: 941

Text #18

Max Range: 0.2858. Min Range: -0.2858

Max Act: 0.2174. Min Act: -0.0001

Data Index: 305482 (C4 (Web Text))

Max Activating Token Index: 631

Text #19

Max Range: 0.2858. Min Range: -0.2858

Max Act: 0.2176. Min Act: -0.0000

Data Index: 955316 (C4 (Web Text))

Max Activating Token Index: 740