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

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

Neuron 2716 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.3798. Min Act: -0.0000

Data Index: 56834 (C4 (Web Text))

Max Activating Token Index: 367

Text #1

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.3306. Min Act: -0.0000

Data Index: 925140 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.3197. Min Act: -0.0000

Data Index: 795969 (C4 (Web Text))

Max Activating Token Index: 743

Text #3

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.3138. Min Act: -0.0000

Data Index: 302026 (C4 (Web Text))

Max Activating Token Index: 534

Text #4

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.2963. Min Act: -0.0000

Data Index: 897368 (C4 (Web Text))

Max Activating Token Index: 888

Text #5

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.3083. Min Act: -0.0000

Data Index: 99050 (C4 (Web Text))

Max Activating Token Index: 347

Text #6

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.2813. Min Act: -0.0000

Data Index: 786386 (C4 (Web Text))

Max Activating Token Index: 57

Text #7

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.2585. Min Act: -0.0000

Data Index: 580913 (C4 (Web Text))

Max Activating Token Index: 984

Text #8

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.2614. Min Act: -0.0000

Data Index: 463300 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.2698. Min Act: 0.0000

Data Index: 148979 (C4 (Web Text))

Max Activating Token Index: 117

Text #10

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.2624. Min Act: -0.0000

Data Index: 1154238 (C4 (Web Text))

Max Activating Token Index: 776

Text #11

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.2603. Min Act: -0.0000

Data Index: 232983 (C4 (Web Text))

Max Activating Token Index: 606

Text #12

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.2369. Min Act: -0.0000

Data Index: 383585 (C4 (Web Text))

Max Activating Token Index: 292

Text #13

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.2188. Min Act: -0.0000

Data Index: 1267707 (C4 (Web Text))

Max Activating Token Index: 464

Text #14

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.2298. Min Act: -0.0000

Data Index: 283536 (C4 (Web Text))

Max Activating Token Index: 229

Text #15

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.2288. Min Act: -0.0000

Data Index: 413808 (C4 (Web Text))

Max Activating Token Index: 314

Text #16

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.2333. Min Act: -0.0000

Data Index: 742532 (C4 (Web Text))

Max Activating Token Index: 754

Text #17

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.2259. Min Act: -0.0000

Data Index: 1300480 (C4 (Web Text))

Max Activating Token Index: 72

Text #18

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.2144. Min Act: -0.0000

Data Index: 540747 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.2185. Min Act: -0.0000

Data Index: 1145126 (C4 (Web Text))

Max Activating Token Index: 410