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

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

Neuron 4172 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: 2.5905. Min Range: -2.5905

Max Act: 2.5905. Min Act: -0.0000

Data Index: 1334917 (C4 (Web Text))

Max Activating Token Index: 1005

Text #1

Max Range: 2.5905. Min Range: -2.5905

Max Act: 2.2136. Min Act: -0.0000

Data Index: 191594 (C4 (Web Text))

Max Activating Token Index: 543

Text #2

Max Range: 2.5905. Min Range: -2.5905

Max Act: 2.0387. Min Act: -0.0000

Data Index: 858071 (C4 (Web Text))

Max Activating Token Index: 132

Text #3

Max Range: 2.5905. Min Range: -2.5905

Max Act: 1.9653. Min Act: -0.0000

Data Index: 865370 (C4 (Web Text))

Max Activating Token Index: 325

Text #4

Max Range: 2.5905. Min Range: -2.5905

Max Act: 2.0080. Min Act: -0.0000

Data Index: 904465 (C4 (Web Text))

Max Activating Token Index: 501

Text #5

Max Range: 2.5905. Min Range: -2.5905

Max Act: 1.7943. Min Act: -0.0000

Data Index: 579913 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 2.5905. Min Range: -2.5905

Max Act: 1.7554. Min Act: -0.0000

Data Index: 680674 (C4 (Web Text))

Max Activating Token Index: 310

Text #7

Max Range: 2.5905. Min Range: -2.5905

Max Act: 1.8581. Min Act: -0.0000

Data Index: 837103 (C4 (Web Text))

Max Activating Token Index: 575

Text #8

Max Range: 2.5905. Min Range: -2.5905

Max Act: 1.6600. Min Act: -0.0000

Data Index: 803659 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 2.5905. Min Range: -2.5905

Max Act: 1.6484. Min Act: -0.0000

Data Index: 863340 (C4 (Web Text))

Max Activating Token Index: 16

Text #10

Max Range: 2.5905. Min Range: -2.5905

Max Act: 1.7666. Min Act: -0.0000

Data Index: 538150 (C4 (Web Text))

Max Activating Token Index: 39

Text #11

Max Range: 2.5905. Min Range: -2.5905

Max Act: 1.6855. Min Act: -0.0000

Data Index: 526915 (C4 (Web Text))

Max Activating Token Index: 850

Text #12

Max Range: 2.5905. Min Range: -2.5905

Max Act: 1.6169. Min Act: -0.0000

Data Index: 566895 (C4 (Web Text))

Max Activating Token Index: 980

Text #13

Max Range: 2.5905. Min Range: -2.5905

Max Act: 1.7695. Min Act: -0.0000

Data Index: 1268722 (C4 (Web Text))

Max Activating Token Index: 41

Text #14

Max Range: 2.5905. Min Range: -2.5905

Max Act: 1.6335. Min Act: -0.0000

Data Index: 1151442 (C4 (Web Text))

Max Activating Token Index: 53

Text #15

Max Range: 2.5905. Min Range: -2.5905

Max Act: 1.5004. Min Act: -0.0000

Data Index: 135186 (C4 (Web Text))

Max Activating Token Index: 796

Text #16

Max Range: 2.5905. Min Range: -2.5905

Max Act: 1.5939. Min Act: -0.0000

Data Index: 288665 (C4 (Web Text))

Max Activating Token Index: 651

Text #17

Max Range: 2.5905. Min Range: -2.5905

Max Act: 1.5486. Min Act: -0.0000

Data Index: 539582 (C4 (Web Text))

Max Activating Token Index: 55

Text #18

Max Range: 2.5905. Min Range: -2.5905

Max Act: 1.5115. Min Act: -0.0000

Data Index: 75928 (C4 (Web Text))

Max Activating Token Index: 118

Text #19

Max Range: 2.5905. Min Range: -2.5905

Max Act: 1.5000. Min Act: -0.0000

Data Index: 898352 (C4 (Web Text))

Max Activating Token Index: 459