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

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

Neuron 589 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.5156. Min Act: -0.0003

Data Index: 1141942 (C4 (Web Text))

Max Activating Token Index: 399

Text #1

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.4695. Min Act: -0.0002

Data Index: 916817 (C4 (Web Text))

Max Activating Token Index: 904

Text #2

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.4351. Min Act: -0.0003

Data Index: 264042 (C4 (Web Text))

Max Activating Token Index: 447

Text #3

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.4383. Min Act: -0.0003

Data Index: 956220 (C4 (Web Text))

Max Activating Token Index: 503

Text #4

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.4183. Min Act: -0.0003

Data Index: 336622 (C4 (Web Text))

Max Activating Token Index: 86

Text #5

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.4229. Min Act: -0.0003

Data Index: 953304 (C4 (Web Text))

Max Activating Token Index: 323

Text #6

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.4106. Min Act: -0.0003

Data Index: 351632 (C4 (Web Text))

Max Activating Token Index: 510

Text #7

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.4188. Min Act: -0.0002

Data Index: 492411 (C4 (Web Text))

Max Activating Token Index: 603

Text #8

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.4161. Min Act: -0.0003

Data Index: 241310 (C4 (Web Text))

Max Activating Token Index: 400

Text #9

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.4127. Min Act: -0.0003

Data Index: 339806 (C4 (Web Text))

Max Activating Token Index: 418

Text #10

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.3980. Min Act: -0.0003

Data Index: 536489 (C4 (Web Text))

Max Activating Token Index: 890

Text #11

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.4098. Min Act: -0.0003

Data Index: 545202 (C4 (Web Text))

Max Activating Token Index: 336

Text #12

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.4090. Min Act: -0.0003

Data Index: 815486 (C4 (Web Text))

Max Activating Token Index: 706

Text #13

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.3928. Min Act: -0.0002

Data Index: 14962 (C4 (Web Text))

Max Activating Token Index: 793

Text #14

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.4055. Min Act: -0.0003

Data Index: 875088 (C4 (Web Text))

Max Activating Token Index: 958

Text #15

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.4048. Min Act: -0.0003

Data Index: 645075 (C4 (Web Text))

Max Activating Token Index: 781

Text #16

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.4039. Min Act: -0.0003

Data Index: 883896 (C4 (Web Text))

Max Activating Token Index: 350

Text #17

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.4041. Min Act: -0.0003

Data Index: 738440 (C4 (Web Text))

Max Activating Token Index: 220

Text #18

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.4025. Min Act: -0.0003

Data Index: 758422 (C4 (Web Text))

Max Activating Token Index: 245

Text #19

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.4031. Min Act: -0.0003

Data Index: 41585 (C4 (Web Text))

Max Activating Token Index: 82