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

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

Neuron 2559 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: 0.5239. Min Range: -0.5239

Max Act: 0.5239. Min Act: -0.0000

Data Index: 834069 (C4 (Web Text))

Max Activating Token Index: 719

Text #1

Max Range: 0.5239. Min Range: -0.5239

Max Act: 0.3792. Min Act: -0.0000

Data Index: 540727 (C4 (Web Text))

Max Activating Token Index: 1005

Text #2

Max Range: 0.5239. Min Range: -0.5239

Max Act: 0.3614. Min Act: -0.0000

Data Index: 723232 (C4 (Web Text))

Max Activating Token Index: 296

Text #3

Max Range: 0.5239. Min Range: -0.5239

Max Act: 0.3298. Min Act: -0.0000

Data Index: 1126902 (C4 (Web Text))

Max Activating Token Index: 357

Text #4

Max Range: 0.5239. Min Range: -0.5239

Max Act: 0.3346. Min Act: -0.0000

Data Index: 243106 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 0.5239. Min Range: -0.5239

Max Act: 0.3268. Min Act: -0.0000

Data Index: 67989 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 0.5239. Min Range: -0.5239

Max Act: 0.3172. Min Act: -0.0000

Data Index: 781889 (C4 (Web Text))

Max Activating Token Index: 981

Text #7

Max Range: 0.5239. Min Range: -0.5239

Max Act: 0.3206. Min Act: -0.0000

Data Index: 110400 (C4 (Web Text))

Max Activating Token Index: 469

Text #8

Max Range: 0.5239. Min Range: -0.5239

Max Act: 0.3254. Min Act: -0.0000

Data Index: 726581 (C4 (Web Text))

Max Activating Token Index: 657

Text #9

Max Range: 0.5239. Min Range: -0.5239

Max Act: 0.3193. Min Act: -0.0000

Data Index: 105876 (C4 (Web Text))

Max Activating Token Index: 741

Text #10

Max Range: 0.5239. Min Range: -0.5239

Max Act: 0.3103. Min Act: 0.0000

Data Index: 411385 (C4 (Web Text))

Max Activating Token Index: 403

Text #11

Max Range: 0.5239. Min Range: -0.5239

Max Act: 0.3162. Min Act: -0.0000

Data Index: 1143371 (C4 (Web Text))

Max Activating Token Index: 450

Text #12

Max Range: 0.5239. Min Range: -0.5239

Max Act: 0.3134. Min Act: -0.0000

Data Index: 142320 (C4 (Web Text))

Max Activating Token Index: 536

Text #13

Max Range: 0.5239. Min Range: -0.5239

Max Act: 0.2946. Min Act: -0.0000

Data Index: 468583 (C4 (Web Text))

Max Activating Token Index: 76

Text #14

Max Range: 0.5239. Min Range: -0.5239

Max Act: 0.2848. Min Act: -0.0000

Data Index: 1004967 (C4 (Web Text))

Max Activating Token Index: 138

Text #15

Max Range: 0.5239. Min Range: -0.5239

Max Act: 0.3019. Min Act: 0.0000

Data Index: 123971 (C4 (Web Text))

Max Activating Token Index: 722

Text #16

Max Range: 0.5239. Min Range: -0.5239

Max Act: 0.2944. Min Act: -0.0000

Data Index: 739987 (C4 (Web Text))

Max Activating Token Index: 41

Text #17

Max Range: 0.5239. Min Range: -0.5239

Max Act: 0.3091. Min Act: -0.0000

Data Index: 307332 (C4 (Web Text))

Max Activating Token Index: 666

Text #18

Max Range: 0.5239. Min Range: -0.5239

Max Act: 0.2973. Min Act: -0.0000

Data Index: 842487 (C4 (Web Text))

Max Activating Token Index: 131

Text #19

Max Range: 0.5239. Min Range: -0.5239

Max Act: 0.2892. Min Act: -0.0000

Data Index: 103384 (C4 (Web Text))

Max Activating Token Index: 535