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

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

Neuron 259 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.8942. Min Act: -0.0001

Data Index: 346346 (C4 (Web Text))

Max Activating Token Index: 385

Text #1

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.8903. Min Act: -0.0001

Data Index: 191919 (C4 (Web Text))

Max Activating Token Index: 968

Text #2

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.9037. Min Act: -0.0000

Data Index: 1043536 (C4 (Web Text))

Max Activating Token Index: 72

Text #3

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.8678. Min Act: -0.0001

Data Index: 987249 (C4 (Web Text))

Max Activating Token Index: 941

Text #4

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.7484. Min Act: -0.0000

Data Index: 338150 (C4 (Web Text))

Max Activating Token Index: 110

Text #5

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.6865. Min Act: -0.0000

Data Index: 688289 (C4 (Web Text))

Max Activating Token Index: 341

Text #6

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.6858. Min Act: -0.0000

Data Index: 630801 (C4 (Web Text))

Max Activating Token Index: 729

Text #7

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.7064. Min Act: -0.0000

Data Index: 333809 (C4 (Web Text))

Max Activating Token Index: 621

Text #8

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.7019. Min Act: -0.0000

Data Index: 921275 (C4 (Web Text))

Max Activating Token Index: 934

Text #9

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.6692. Min Act: -0.0000

Data Index: 278335 (C4 (Web Text))

Max Activating Token Index: 712

Text #10

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.6823. Min Act: -0.0001

Data Index: 757448 (C4 (Web Text))

Max Activating Token Index: 683

Text #11

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.6417. Min Act: -0.0001

Data Index: 938218 (C4 (Web Text))

Max Activating Token Index: 819

Text #12

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.6157. Min Act: -0.0000

Data Index: 45084 (C4 (Web Text))

Max Activating Token Index: 266

Text #13

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.6299. Min Act: -0.0001

Data Index: 647289 (C4 (Web Text))

Max Activating Token Index: 458

Text #14

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.5886. Min Act: -0.0001

Data Index: 910449 (C4 (Web Text))

Max Activating Token Index: 993

Text #15

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.6180. Min Act: -0.0000

Data Index: 880235 (C4 (Web Text))

Max Activating Token Index: 547

Text #16

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.6045. Min Act: 0.0000

Data Index: 68876 (C4 (Web Text))

Max Activating Token Index: 745

Text #17

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.6165. Min Act: -0.0000

Data Index: 570488 (C4 (Web Text))

Max Activating Token Index: 610

Text #18

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.6105. Min Act: -0.0000

Data Index: 1160712 (C4 (Web Text))

Max Activating Token Index: 963

Text #19

Max Range: 0.9037. Min Range: -0.9037

Max Act: 0.5989. Min Act: 0.0001

Data Index: 24914 (C4 (Web Text))

Max Activating Token Index: 436