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

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

Neuron 5243 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0223. Min Range: -1.0223

Max Act: 1.0223. Min Act: -0.0000

Data Index: 108731 (C4 (Web Text))

Max Activating Token Index: 55

Text #1

Max Range: 1.0223. Min Range: -1.0223

Max Act: 0.9535. Min Act: -0.0000

Data Index: 436580 (C4 (Web Text))

Max Activating Token Index: 1007

Text #2

Max Range: 1.0223. Min Range: -1.0223

Max Act: 0.8535. Min Act: -0.0000

Data Index: 431234 (C4 (Web Text))

Max Activating Token Index: 601

Text #3

Max Range: 1.0223. Min Range: -1.0223

Max Act: 0.8166. Min Act: -0.0000

Data Index: 347962 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 1.0223. Min Range: -1.0223

Max Act: 0.8114. Min Act: -0.0000

Data Index: 965096 (C4 (Web Text))

Max Activating Token Index: 577

Text #5

Max Range: 1.0223. Min Range: -1.0223

Max Act: 0.8174. Min Act: -0.0000

Data Index: 1068614 (C4 (Web Text))

Max Activating Token Index: 612

Text #6

Max Range: 1.0223. Min Range: -1.0223

Max Act: 0.8022. Min Act: -0.0000

Data Index: 1059109 (C4 (Web Text))

Max Activating Token Index: 618

Text #7

Max Range: 1.0223. Min Range: -1.0223

Max Act: 0.7994. Min Act: -0.0000

Data Index: 890740 (C4 (Web Text))

Max Activating Token Index: 474

Text #8

Max Range: 1.0223. Min Range: -1.0223

Max Act: 0.8093. Min Act: -0.0000

Data Index: 1010138 (C4 (Web Text))

Max Activating Token Index: 973

Text #9

Max Range: 1.0223. Min Range: -1.0223

Max Act: 0.7605. Min Act: -0.0000

Data Index: 110569 (C4 (Web Text))

Max Activating Token Index: 905

Text #10

Max Range: 1.0223. Min Range: -1.0223

Max Act: 0.7856. Min Act: -0.0000

Data Index: 652319 (C4 (Web Text))

Max Activating Token Index: 694

Text #11

Max Range: 1.0223. Min Range: -1.0223

Max Act: 0.7295. Min Act: -0.0000

Data Index: 924373 (C4 (Web Text))

Max Activating Token Index: 783

Text #12

Max Range: 1.0223. Min Range: -1.0223

Max Act: 0.7247. Min Act: -0.0000

Data Index: 674152 (C4 (Web Text))

Max Activating Token Index: 805

Text #13

Max Range: 1.0223. Min Range: -1.0223

Max Act: 0.7615. Min Act: -0.0000

Data Index: 590062 (C4 (Web Text))

Max Activating Token Index: 199

Text #14

Max Range: 1.0223. Min Range: -1.0223

Max Act: 0.7587. Min Act: -0.0000

Data Index: 1110130 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 1.0223. Min Range: -1.0223

Max Act: 0.7543. Min Act: -0.0000

Data Index: 1284344 (C4 (Web Text))

Max Activating Token Index: 779

Text #16

Max Range: 1.0223. Min Range: -1.0223

Max Act: 0.7272. Min Act: -0.0000

Data Index: 1177786 (C4 (Web Text))

Max Activating Token Index: 608

Text #17

Max Range: 1.0223. Min Range: -1.0223

Max Act: 0.7792. Min Act: -0.0000

Data Index: 883736 (C4 (Web Text))

Max Activating Token Index: 720

Text #18

Max Range: 1.0223. Min Range: -1.0223

Max Act: 0.7500. Min Act: -0.0000

Data Index: 1208124 (C4 (Web Text))

Max Activating Token Index: 271

Text #19

Max Range: 1.0223. Min Range: -1.0223

Max Act: 0.7382. Min Act: -0.0000

Data Index: 134706 (C4 (Web Text))

Max Activating Token Index: 271