Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 878 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.7877. Min Act: -0.0001

Data Index: 136583 (C4 (Web Text))

Max Activating Token Index: 704

Text #1

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.7091. Min Act: -0.0001

Data Index: 429513 (C4 (Web Text))

Max Activating Token Index: 367

Text #2

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.6735. Min Act: -0.0001

Data Index: 777780 (C4 (Web Text))

Max Activating Token Index: 724

Text #3

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.6397. Min Act: -0.0001

Data Index: 335144 (C4 (Web Text))

Max Activating Token Index: 558

Text #4

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.6154. Min Act: -0.0001

Data Index: 1341873 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.6151. Min Act: -0.0001

Data Index: 347755 (C4 (Web Text))

Max Activating Token Index: 952

Text #6

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.6083. Min Act: -0.0001

Data Index: 1241887 (C4 (Web Text))

Max Activating Token Index: 445

Text #7

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.5983. Min Act: -0.0001

Data Index: 153732 (C4 (Web Text))

Max Activating Token Index: 518

Text #8

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.5925. Min Act: -0.0001

Data Index: 1210304 (C4 (Web Text))

Max Activating Token Index: 102

Text #9

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.5715. Min Act: -0.0000

Data Index: 34907 (C4 (Web Text))

Max Activating Token Index: 54

Text #10

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.5508. Min Act: -0.0001

Data Index: 262598 (C4 (Web Text))

Max Activating Token Index: 922

Text #11

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.5543. Min Act: -0.0001

Data Index: 1294822 (C4 (Web Text))

Max Activating Token Index: 835

Text #12

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.5584. Min Act: -0.0001

Data Index: 1190049 (C4 (Web Text))

Max Activating Token Index: 561

Text #13

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.5851. Min Act: -0.0001

Data Index: 658600 (C4 (Web Text))

Max Activating Token Index: 344

Text #14

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.5270. Min Act: -0.0001

Data Index: 1130164 (C4 (Web Text))

Max Activating Token Index: 264

Text #15

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.5233. Min Act: -0.0001

Data Index: 485628 (C4 (Web Text))

Max Activating Token Index: 704

Text #16

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.4894. Min Act: -0.0001

Data Index: 1188326 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.5043. Min Act: -0.0001

Data Index: 173320 (C4 (Web Text))

Max Activating Token Index: 186

Text #18

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.4965. Min Act: -0.0001

Data Index: 566777 (C4 (Web Text))

Max Activating Token Index: 588

Text #19

Max Range: 0.7877. Min Range: -0.7877

Max Act: 0.5302. Min Act: -0.0001

Data Index: 230578 (C4 (Web Text))

Max Activating Token Index: 894