Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 214 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9196. Min Range: -0.9196

Max Act: 0.8225. Min Act: -0.0001

Data Index: 699380 (C4 (Web Text))

Max Activating Token Index: 615

Text #1

Max Range: 0.9196. Min Range: -0.9196

Max Act: 0.8809. Min Act: -0.0001

Data Index: 395673 (C4 (Web Text))

Max Activating Token Index: 674

Text #2

Max Range: 0.9196. Min Range: -0.9196

Max Act: 0.9072. Min Act: -0.0001

Data Index: 1034766 (C4 (Web Text))

Max Activating Token Index: 454

Text #3

Max Range: 0.9196. Min Range: -0.9196

Max Act: 0.9196. Min Act: -0.0001

Data Index: 113512 (C4 (Web Text))

Max Activating Token Index: 473

Text #4

Max Range: 0.9196. Min Range: -0.9196

Max Act: 0.8828. Min Act: -0.0001

Data Index: 341550 (C4 (Web Text))

Max Activating Token Index: 641

Text #5

Max Range: 0.9196. Min Range: -0.9196

Max Act: 0.7969. Min Act: -0.0001

Data Index: 25362 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 0.9196. Min Range: -0.9196

Max Act: 0.7737. Min Act: -0.0001

Data Index: 769119 (C4 (Web Text))

Max Activating Token Index: 561

Text #7

Max Range: 0.9196. Min Range: -0.9196

Max Act: 0.7132. Min Act: -0.0001

Data Index: 415363 (C4 (Web Text))

Max Activating Token Index: 684

Text #8

Max Range: 0.9196. Min Range: -0.9196

Max Act: 0.7422. Min Act: -0.0001

Data Index: 166259 (C4 (Web Text))

Max Activating Token Index: 484

Text #9

Max Range: 0.9196. Min Range: -0.9196

Max Act: 0.8092. Min Act: -0.0001

Data Index: 756587 (C4 (Web Text))

Max Activating Token Index: 562

Text #10

Max Range: 0.9196. Min Range: -0.9196

Max Act: 0.8133. Min Act: -0.0001

Data Index: 1086396 (C4 (Web Text))

Max Activating Token Index: 807

Text #11

Max Range: 0.9196. Min Range: -0.9196

Max Act: 0.7529. Min Act: -0.0001

Data Index: 474830 (C4 (Web Text))

Max Activating Token Index: 223

Text #12

Max Range: 0.9196. Min Range: -0.9196

Max Act: 0.7755. Min Act: -0.0001

Data Index: 485577 (C4 (Web Text))

Max Activating Token Index: 895

Text #13

Max Range: 0.9196. Min Range: -0.9196

Max Act: 0.7735. Min Act: -0.0001

Data Index: 427176 (C4 (Web Text))

Max Activating Token Index: 514

Text #14

Max Range: 0.9196. Min Range: -0.9196

Max Act: 0.7148. Min Act: -0.0001

Data Index: 996767 (C4 (Web Text))

Max Activating Token Index: 939

Text #15

Max Range: 0.9196. Min Range: -0.9196

Max Act: 0.7559. Min Act: -0.0001

Data Index: 645476 (C4 (Web Text))

Max Activating Token Index: 708

Text #16

Max Range: 0.9196. Min Range: -0.9196

Max Act: 0.7285. Min Act: -0.0001

Data Index: 973542 (C4 (Web Text))

Max Activating Token Index: 907

Text #17

Max Range: 0.9196. Min Range: -0.9196

Max Act: 0.7495. Min Act: -0.0001

Data Index: 356264 (C4 (Web Text))

Max Activating Token Index: 130

Text #18

Max Range: 0.9196. Min Range: -0.9196

Max Act: 0.6927. Min Act: -0.0001

Data Index: 751997 (C4 (Web Text))

Max Activating Token Index: 587

Text #19

Max Range: 0.9196. Min Range: -0.9196

Max Act: 0.7145. Min Act: -0.0001

Data Index: 981902 (C4 (Web Text))

Max Activating Token Index: 847