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

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

Neuron 683 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.5154. Min Range: -7.5154

Max Act: 7.5154. Min Act: -0.0000

Data Index: 677911 (C4 (Web Text))

Max Activating Token Index: 147

Text #1

Max Range: 7.5154. Min Range: -7.5154

Max Act: 6.9348. Min Act: -0.0000

Data Index: 676057 (C4 (Web Text))

Max Activating Token Index: 828

Text #2

Max Range: 7.5154. Min Range: -7.5154

Max Act: 6.2873. Min Act: -0.0000

Data Index: 619759 (C4 (Web Text))

Max Activating Token Index: 52

Text #3

Max Range: 7.5154. Min Range: -7.5154

Max Act: 6.2411. Min Act: -0.0000

Data Index: 1271891 (C4 (Web Text))

Max Activating Token Index: 723

Text #4

Max Range: 7.5154. Min Range: -7.5154

Max Act: 6.2193. Min Act: -0.0000

Data Index: 740099 (C4 (Web Text))

Max Activating Token Index: 733

Text #5

Max Range: 7.5154. Min Range: -7.5154

Max Act: 5.8463. Min Act: -0.0000

Data Index: 634153 (C4 (Web Text))

Max Activating Token Index: 375

Text #6

Max Range: 7.5154. Min Range: -7.5154

Max Act: 5.8465. Min Act: -0.0000

Data Index: 681121 (C4 (Web Text))

Max Activating Token Index: 486

Text #7

Max Range: 7.5154. Min Range: -7.5154

Max Act: 6.2021. Min Act: -0.0000

Data Index: 62697 (C4 (Web Text))

Max Activating Token Index: 829

Text #8

Max Range: 7.5154. Min Range: -7.5154

Max Act: 6.3288. Min Act: -0.0000

Data Index: 135157 (C4 (Web Text))

Max Activating Token Index: 413

Text #9

Max Range: 7.5154. Min Range: -7.5154

Max Act: 5.6014. Min Act: -0.0000

Data Index: 660813 (C4 (Web Text))

Max Activating Token Index: 289

Text #10

Max Range: 7.5154. Min Range: -7.5154

Max Act: 5.8824. Min Act: -0.0000

Data Index: 470107 (C4 (Web Text))

Max Activating Token Index: 724

Text #11

Max Range: 7.5154. Min Range: -7.5154

Max Act: 5.1045. Min Act: -0.0000

Data Index: 398576 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 7.5154. Min Range: -7.5154

Max Act: 5.6659. Min Act: -0.0000

Data Index: 285846 (C4 (Web Text))

Max Activating Token Index: 427

Text #13

Max Range: 7.5154. Min Range: -7.5154

Max Act: 4.6558. Min Act: -0.0000

Data Index: 193957 (C4 (Web Text))

Max Activating Token Index: 252

Text #14

Max Range: 7.5154. Min Range: -7.5154

Max Act: 5.2091. Min Act: -0.0000

Data Index: 1086235 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 7.5154. Min Range: -7.5154

Max Act: 5.0361. Min Act: -0.0000

Data Index: 1216022 (C4 (Web Text))

Max Activating Token Index: 779

Text #16

Max Range: 7.5154. Min Range: -7.5154

Max Act: 5.0047. Min Act: -0.0000

Data Index: 747507 (C4 (Web Text))

Max Activating Token Index: 26

Text #17

Max Range: 7.5154. Min Range: -7.5154

Max Act: 5.5834. Min Act: -0.0000

Data Index: 835264 (C4 (Web Text))

Max Activating Token Index: 380

Text #18

Max Range: 7.5154. Min Range: -7.5154

Max Act: 5.3630. Min Act: -0.0000

Data Index: 52736 (C4 (Web Text))

Max Activating Token Index: 616

Text #19

Max Range: 7.5154. Min Range: -7.5154

Max Act: 5.1167. Min Act: -0.0000

Data Index: 1188656 (C4 (Web Text))

Max Activating Token Index: 394