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

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

Neuron 4626 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: 1.4240. Min Range: -1.4240

Max Act: 1.4197. Min Act: -0.0000

Data Index: 1080744 (C4 (Web Text))

Max Activating Token Index: 121

Text #1

Max Range: 1.4240. Min Range: -1.4240

Max Act: 1.3575. Min Act: -0.0000

Data Index: 1040902 (C4 (Web Text))

Max Activating Token Index: 117

Text #2

Max Range: 1.4240. Min Range: -1.4240

Max Act: 1.4240. Min Act: -0.0000

Data Index: 977158 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 1.4240. Min Range: -1.4240

Max Act: 1.3500. Min Act: -0.0000

Data Index: 1160176 (C4 (Web Text))

Max Activating Token Index: 925

Text #4

Max Range: 1.4240. Min Range: -1.4240

Max Act: 1.3536. Min Act: -0.0000

Data Index: 469720 (C4 (Web Text))

Max Activating Token Index: 366

Text #5

Max Range: 1.4240. Min Range: -1.4240

Max Act: 1.2683. Min Act: -0.0000

Data Index: 671820 (C4 (Web Text))

Max Activating Token Index: 298

Text #6

Max Range: 1.4240. Min Range: -1.4240

Max Act: 1.2206. Min Act: -0.0000

Data Index: 503400 (C4 (Web Text))

Max Activating Token Index: 476

Text #7

Max Range: 1.4240. Min Range: -1.4240

Max Act: 1.3671. Min Act: -0.0000

Data Index: 545688 (C4 (Web Text))

Max Activating Token Index: 87

Text #8

Max Range: 1.4240. Min Range: -1.4240

Max Act: 1.2339. Min Act: -0.0000

Data Index: 334911 (C4 (Web Text))

Max Activating Token Index: 21

Text #9

Max Range: 1.4240. Min Range: -1.4240

Max Act: 1.2938. Min Act: -0.0000

Data Index: 1219386 (C4 (Web Text))

Max Activating Token Index: 422

Text #10

Max Range: 1.4240. Min Range: -1.4240

Max Act: 1.2137. Min Act: -0.0000

Data Index: 320261 (C4 (Web Text))

Max Activating Token Index: 859

Text #11

Max Range: 1.4240. Min Range: -1.4240

Max Act: 1.2069. Min Act: -0.0000

Data Index: 1113236 (C4 (Web Text))

Max Activating Token Index: 197

Text #12

Max Range: 1.4240. Min Range: -1.4240

Max Act: 1.1968. Min Act: -0.0000

Data Index: 1030603 (C4 (Web Text))

Max Activating Token Index: 123

Text #13

Max Range: 1.4240. Min Range: -1.4240

Max Act: 1.1990. Min Act: -0.0000

Data Index: 659304 (C4 (Web Text))

Max Activating Token Index: 999

Text #14

Max Range: 1.4240. Min Range: -1.4240

Max Act: 1.1860. Min Act: -0.0000

Data Index: 868713 (C4 (Web Text))

Max Activating Token Index: 208

Text #15

Max Range: 1.4240. Min Range: -1.4240

Max Act: 1.1881. Min Act: -0.0000

Data Index: 1282857 (C4 (Web Text))

Max Activating Token Index: 229

Text #16

Max Range: 1.4240. Min Range: -1.4240

Max Act: 1.1133. Min Act: -0.0000

Data Index: 489684 (C4 (Web Text))

Max Activating Token Index: 877

Text #17

Max Range: 1.4240. Min Range: -1.4240

Max Act: 1.1659. Min Act: -0.0000

Data Index: 37503 (C4 (Web Text))

Max Activating Token Index: 247

Text #18

Max Range: 1.4240. Min Range: -1.4240

Max Act: 1.1510. Min Act: -0.0000

Data Index: 1345027 (C4 (Web Text))

Max Activating Token Index: 605

Text #19

Max Range: 1.4240. Min Range: -1.4240

Max Act: 1.2115. Min Act: -0.0000

Data Index: 75073 (C4 (Web Text))

Max Activating Token Index: 752