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

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

Neuron 2762 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.7530. Min Act: -0.0000

Data Index: 925198 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.5796. Min Act: -0.0000

Data Index: 584205 (C4 (Web Text))

Max Activating Token Index: 357

Text #2

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.5207. Min Act: -0.0000

Data Index: 174184 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.5573. Min Act: -0.0000

Data Index: 805684 (C4 (Web Text))

Max Activating Token Index: 90

Text #4

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.5111. Min Act: -0.0000

Data Index: 109052 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.4807. Min Act: -0.0000

Data Index: 1206484 (C4 (Web Text))

Max Activating Token Index: 786

Text #6

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.4628. Min Act: -0.0000

Data Index: 420938 (C4 (Web Text))

Max Activating Token Index: 852

Text #7

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.4067. Min Act: -0.0000

Data Index: 613384 (C4 (Web Text))

Max Activating Token Index: 360

Text #8

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.4250. Min Act: -0.0000

Data Index: 18215 (C4 (Web Text))

Max Activating Token Index: 133

Text #9

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.4195. Min Act: -0.0000

Data Index: 529273 (C4 (Web Text))

Max Activating Token Index: 235

Text #10

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.4302. Min Act: -0.0000

Data Index: 1201796 (C4 (Web Text))

Max Activating Token Index: 355

Text #11

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.4219. Min Act: -0.0000

Data Index: 1261737 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.4064. Min Act: -0.0000

Data Index: 715637 (C4 (Web Text))

Max Activating Token Index: 400

Text #13

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.4091. Min Act: -0.0000

Data Index: 475067 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.4078. Min Act: -0.0000

Data Index: 591668 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.3737. Min Act: -0.0000

Data Index: 151850 (C4 (Web Text))

Max Activating Token Index: 207

Text #16

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.3882. Min Act: -0.0000

Data Index: 932718 (C4 (Web Text))

Max Activating Token Index: 198

Text #17

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.3862. Min Act: -0.0000

Data Index: 959563 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.3972. Min Act: -0.0000

Data Index: 945692 (C4 (Web Text))

Max Activating Token Index: 144

Text #19

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.4691. Min Act: -0.0000

Data Index: 1170942 (C4 (Web Text))

Max Activating Token Index: 817