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

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

Neuron 5140 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.8901. Min Act: -0.0000

Data Index: 250418 (C4 (Web Text))

Max Activating Token Index: 406

Text #1

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.8231. Min Act: -0.0000

Data Index: 312379 (C4 (Web Text))

Max Activating Token Index: 122

Text #2

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.8202. Min Act: -0.0000

Data Index: 1220658 (C4 (Web Text))

Max Activating Token Index: 205

Text #3

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.7769. Min Act: -0.0000

Data Index: 840344 (C4 (Web Text))

Max Activating Token Index: 865

Text #4

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.7450. Min Act: -0.0000

Data Index: 1190358 (C4 (Web Text))

Max Activating Token Index: 982

Text #5

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.6515. Min Act: -0.0000

Data Index: 1116402 (C4 (Web Text))

Max Activating Token Index: 992

Text #6

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.6908. Min Act: -0.0000

Data Index: 467258 (C4 (Web Text))

Max Activating Token Index: 518

Text #7

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.6757. Min Act: -0.0000

Data Index: 923443 (C4 (Web Text))

Max Activating Token Index: 791

Text #8

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.6137. Min Act: -0.0000

Data Index: 787290 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.6012. Min Act: -0.0000

Data Index: 1231874 (C4 (Web Text))

Max Activating Token Index: 801

Text #10

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.5596. Min Act: -0.0000

Data Index: 204514 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.6266. Min Act: -0.0000

Data Index: 146682 (C4 (Web Text))

Max Activating Token Index: 198

Text #12

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.5429. Min Act: -0.0000

Data Index: 695650 (C4 (Web Text))

Max Activating Token Index: 58

Text #13

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.5122. Min Act: -0.0000

Data Index: 32183 (C4 (Web Text))

Max Activating Token Index: 316

Text #14

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.4579. Min Act: -0.0000

Data Index: 547040 (C4 (Web Text))

Max Activating Token Index: 583

Text #15

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.5061. Min Act: -0.0000

Data Index: 1299933 (C4 (Web Text))

Max Activating Token Index: 98

Text #16

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.4708. Min Act: -0.0000

Data Index: 1084072 (C4 (Web Text))

Max Activating Token Index: 779

Text #17

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.3961. Min Act: -0.0000

Data Index: 31102 (C4 (Web Text))

Max Activating Token Index: 556

Text #18

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.3932. Min Act: -0.0000

Data Index: 265185 (C4 (Web Text))

Max Activating Token Index: 378

Text #19

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.4281. Min Act: -0.0000

Data Index: 112527 (C4 (Web Text))

Max Activating Token Index: 297