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

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

Neuron 2463 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3161. Min Range: -1.3161

Max Act: 1.3161. Min Act: -0.0000

Data Index: 524354 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 1.3161. Min Range: -1.3161

Max Act: 1.1458. Min Act: -0.0000

Data Index: 331029 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 1.3161. Min Range: -1.3161

Max Act: 1.0509. Min Act: -0.0000

Data Index: 795501 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 1.3161. Min Range: -1.3161

Max Act: 1.1126. Min Act: -0.0000

Data Index: 96771 (C4 (Web Text))

Max Activating Token Index: 25

Text #4

Max Range: 1.3161. Min Range: -1.3161

Max Act: 1.0900. Min Act: -0.0000

Data Index: 1248009 (C4 (Web Text))

Max Activating Token Index: 698

Text #5

Max Range: 1.3161. Min Range: -1.3161

Max Act: 1.0851. Min Act: -0.0000

Data Index: 43683 (C4 (Web Text))

Max Activating Token Index: 114

Text #6

Max Range: 1.3161. Min Range: -1.3161

Max Act: 0.9121. Min Act: -0.0000

Data Index: 258161 (C4 (Web Text))

Max Activating Token Index: 574

Text #7

Max Range: 1.3161. Min Range: -1.3161

Max Act: 0.9145. Min Act: -0.0000

Data Index: 1004307 (C4 (Web Text))

Max Activating Token Index: 722

Text #8

Max Range: 1.3161. Min Range: -1.3161

Max Act: 0.9753. Min Act: -0.0000

Data Index: 1337527 (C4 (Web Text))

Max Activating Token Index: 296

Text #9

Max Range: 1.3161. Min Range: -1.3161

Max Act: 0.9148. Min Act: -0.0000

Data Index: 1077111 (C4 (Web Text))

Max Activating Token Index: 390

Text #10

Max Range: 1.3161. Min Range: -1.3161

Max Act: 0.7659. Min Act: -0.0000

Data Index: 1319681 (C4 (Web Text))

Max Activating Token Index: 27

Text #11

Max Range: 1.3161. Min Range: -1.3161

Max Act: 0.7691. Min Act: -0.0000

Data Index: 1267193 (C4 (Web Text))

Max Activating Token Index: 978

Text #12

Max Range: 1.3161. Min Range: -1.3161

Max Act: 0.7748. Min Act: -0.0000

Data Index: 1213282 (C4 (Web Text))

Max Activating Token Index: 883

Text #13

Max Range: 1.3161. Min Range: -1.3161

Max Act: 0.7315. Min Act: -0.0000

Data Index: 181010 (C4 (Web Text))

Max Activating Token Index: 788

Text #14

Max Range: 1.3161. Min Range: -1.3161

Max Act: 0.7195. Min Act: -0.0000

Data Index: 774825 (C4 (Web Text))

Max Activating Token Index: 1014

Text #15

Max Range: 1.3161. Min Range: -1.3161

Max Act: 0.7800. Min Act: -0.0000

Data Index: 1431982 (Python Code)

Max Activating Token Index: 681

Text #16

Max Range: 1.3161. Min Range: -1.3161

Max Act: 0.8280. Min Act: -0.0000

Data Index: 108703 (C4 (Web Text))

Max Activating Token Index: 616

Text #17

Max Range: 1.3161. Min Range: -1.3161

Max Act: 0.7152. Min Act: -0.0000

Data Index: 714118 (C4 (Web Text))

Max Activating Token Index: 863

Text #18

Max Range: 1.3161. Min Range: -1.3161

Max Act: 0.7327. Min Act: -0.0000

Data Index: 620929 (C4 (Web Text))

Max Activating Token Index: 471

Text #19

Max Range: 1.3161. Min Range: -1.3161

Max Act: 0.7226. Min Act: -0.0000

Data Index: 867839 (C4 (Web Text))

Max Activating Token Index: 284