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

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

Neuron 402 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.3253. Min Act: -0.0003

Data Index: 792884 (C4 (Web Text))

Max Activating Token Index: 869

Text #1

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.3353. Min Act: -0.0003

Data Index: 591035 (C4 (Web Text))

Max Activating Token Index: 813

Text #2

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.3195. Min Act: -0.0003

Data Index: 367607 (C4 (Web Text))

Max Activating Token Index: 165

Text #3

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.3333. Min Act: -0.0003

Data Index: 415363 (C4 (Web Text))

Max Activating Token Index: 723

Text #4

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.3265. Min Act: -0.0003

Data Index: 932066 (C4 (Web Text))

Max Activating Token Index: 351

Text #5

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.3245. Min Act: -0.0003

Data Index: 436400 (C4 (Web Text))

Max Activating Token Index: 963

Text #6

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.3232. Min Act: -0.0003

Data Index: 1337635 (C4 (Web Text))

Max Activating Token Index: 14

Text #7

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.3129. Min Act: -0.0003

Data Index: 714003 (C4 (Web Text))

Max Activating Token Index: 851

Text #8

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.2939. Min Act: -0.0002

Data Index: 87069 (C4 (Web Text))

Max Activating Token Index: 1019

Text #9

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.3053. Min Act: -0.0003

Data Index: 320646 (C4 (Web Text))

Max Activating Token Index: 376

Text #10

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.3110. Min Act: -0.0003

Data Index: 883670 (C4 (Web Text))

Max Activating Token Index: 148

Text #11

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.3051. Min Act: -0.0003

Data Index: 679682 (C4 (Web Text))

Max Activating Token Index: 636

Text #12

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.3068. Min Act: -0.0003

Data Index: 955338 (C4 (Web Text))

Max Activating Token Index: 349

Text #13

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.2964. Min Act: -0.0003

Data Index: 1254700 (C4 (Web Text))

Max Activating Token Index: 150

Text #14

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.3041. Min Act: -0.0003

Data Index: 425181 (C4 (Web Text))

Max Activating Token Index: 152

Text #15

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.2811. Min Act: -0.0003

Data Index: 1215247 (C4 (Web Text))

Max Activating Token Index: 654

Text #16

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.2798. Min Act: -0.0002

Data Index: 162634 (C4 (Web Text))

Max Activating Token Index: 893

Text #17

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.2886. Min Act: -0.0002

Data Index: 78111 (C4 (Web Text))

Max Activating Token Index: 546

Text #18

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.2869. Min Act: -0.0003

Data Index: 387542 (C4 (Web Text))

Max Activating Token Index: 570

Text #19

Max Range: 0.3353. Min Range: -0.3353

Max Act: 0.2872. Min Act: -0.0003

Data Index: 331799 (C4 (Web Text))

Max Activating Token Index: 729