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

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

Neuron 3125 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: 0.4118. Min Range: -0.4118

Max Act: 0.4118. Min Act: -0.0000

Data Index: 600963 (C4 (Web Text))

Max Activating Token Index: 925

Text #1

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.3036. Min Act: -0.0000

Data Index: 394377 (C4 (Web Text))

Max Activating Token Index: 786

Text #2

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.3972. Min Act: -0.0000

Data Index: 631874 (C4 (Web Text))

Max Activating Token Index: 920

Text #3

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.3730. Min Act: -0.0000

Data Index: 229843 (C4 (Web Text))

Max Activating Token Index: 1000

Text #4

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.2878. Min Act: -0.0000

Data Index: 436431 (C4 (Web Text))

Max Activating Token Index: 116

Text #5

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.3476. Min Act: -0.0000

Data Index: 814889 (C4 (Web Text))

Max Activating Token Index: 326

Text #6

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.3166. Min Act: -0.0000

Data Index: 896610 (C4 (Web Text))

Max Activating Token Index: 871

Text #7

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.2817. Min Act: -0.0000

Data Index: 1163210 (C4 (Web Text))

Max Activating Token Index: 185

Text #8

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.3431. Min Act: -0.0000

Data Index: 71473 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.3058. Min Act: -0.0000

Data Index: 99738 (C4 (Web Text))

Max Activating Token Index: 590

Text #10

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.3080. Min Act: -0.0000

Data Index: 1091363 (C4 (Web Text))

Max Activating Token Index: 940

Text #11

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.3408. Min Act: -0.0000

Data Index: 792079 (C4 (Web Text))

Max Activating Token Index: 119

Text #12

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.2913. Min Act: -0.0000

Data Index: 516799 (C4 (Web Text))

Max Activating Token Index: 800

Text #13

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.2766. Min Act: -0.0000

Data Index: 1258572 (C4 (Web Text))

Max Activating Token Index: 861

Text #14

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.2884. Min Act: -0.0000

Data Index: 788480 (C4 (Web Text))

Max Activating Token Index: 973

Text #15

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.2618. Min Act: -0.0000

Data Index: 451726 (C4 (Web Text))

Max Activating Token Index: 753

Text #16

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.2434. Min Act: -0.0000

Data Index: 455020 (C4 (Web Text))

Max Activating Token Index: 718

Text #17

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.2886. Min Act: -0.0000

Data Index: 668010 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.2840. Min Act: -0.0000

Data Index: 426248 (C4 (Web Text))

Max Activating Token Index: 358

Text #19

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.2606. Min Act: -0.0000

Data Index: 829737 (C4 (Web Text))

Max Activating Token Index: 974