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

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

Neuron 1665 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8154. Min Range: -1.8154

Max Act: 1.8154. Min Act: -0.0000

Data Index: 432925 (C4 (Web Text))

Max Activating Token Index: 876

Text #1

Max Range: 1.8154. Min Range: -1.8154

Max Act: 1.7224. Min Act: -0.0001

Data Index: 1026202 (C4 (Web Text))

Max Activating Token Index: 168

Text #2

Max Range: 1.8154. Min Range: -1.8154

Max Act: 1.2341. Min Act: -0.0001

Data Index: 190149 (C4 (Web Text))

Max Activating Token Index: 672

Text #3

Max Range: 1.8154. Min Range: -1.8154

Max Act: 1.1942. Min Act: -0.0000

Data Index: 943413 (C4 (Web Text))

Max Activating Token Index: 789

Text #4

Max Range: 1.8154. Min Range: -1.8154

Max Act: 1.1593. Min Act: -0.0000

Data Index: 1019868 (C4 (Web Text))

Max Activating Token Index: 532

Text #5

Max Range: 1.8154. Min Range: -1.8154

Max Act: 1.1086. Min Act: -0.0000

Data Index: 869008 (C4 (Web Text))

Max Activating Token Index: 675

Text #6

Max Range: 1.8154. Min Range: -1.8154

Max Act: 1.1299. Min Act: -0.0001

Data Index: 67922 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 1.8154. Min Range: -1.8154

Max Act: 1.1033. Min Act: -0.0000

Data Index: 1206106 (C4 (Web Text))

Max Activating Token Index: 202

Text #8

Max Range: 1.8154. Min Range: -1.8154

Max Act: 0.9951. Min Act: -0.0001

Data Index: 105898 (C4 (Web Text))

Max Activating Token Index: 787

Text #9

Max Range: 1.8154. Min Range: -1.8154

Max Act: 1.0409. Min Act: -0.0001

Data Index: 1188412 (C4 (Web Text))

Max Activating Token Index: 92

Text #10

Max Range: 1.8154. Min Range: -1.8154

Max Act: 1.0472. Min Act: -0.0000

Data Index: 7786 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 1.8154. Min Range: -1.8154

Max Act: 1.0745. Min Act: -0.0000

Data Index: 381056 (C4 (Web Text))

Max Activating Token Index: 308

Text #12

Max Range: 1.8154. Min Range: -1.8154

Max Act: 1.0300. Min Act: -0.0001

Data Index: 1323715 (C4 (Web Text))

Max Activating Token Index: 225

Text #13

Max Range: 1.8154. Min Range: -1.8154

Max Act: 1.0973. Min Act: -0.0001

Data Index: 151572 (C4 (Web Text))

Max Activating Token Index: 884

Text #14

Max Range: 1.8154. Min Range: -1.8154

Max Act: 0.9915. Min Act: -0.0001

Data Index: 933845 (C4 (Web Text))

Max Activating Token Index: 261

Text #15

Max Range: 1.8154. Min Range: -1.8154

Max Act: 1.0481. Min Act: -0.0000

Data Index: 351009 (C4 (Web Text))

Max Activating Token Index: 562

Text #16

Max Range: 1.8154. Min Range: -1.8154

Max Act: 1.0516. Min Act: -0.0000

Data Index: 377266 (C4 (Web Text))

Max Activating Token Index: 247

Text #17

Max Range: 1.8154. Min Range: -1.8154

Max Act: 1.0475. Min Act: -0.0000

Data Index: 844849 (C4 (Web Text))

Max Activating Token Index: 825

Text #18

Max Range: 1.8154. Min Range: -1.8154

Max Act: 1.0478. Min Act: -0.0000

Data Index: 1008093 (C4 (Web Text))

Max Activating Token Index: 814

Text #19

Max Range: 1.8154. Min Range: -1.8154

Max Act: 1.0164. Min Act: -0.0001

Data Index: 761056 (C4 (Web Text))

Max Activating Token Index: 556