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

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

Neuron 2542 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1297. Min Range: -1.1297

Max Act: 1.1297. Min Act: -0.0001

Data Index: 159289 (C4 (Web Text))

Max Activating Token Index: 720

Text #1

Max Range: 1.1297. Min Range: -1.1297

Max Act: 0.9470. Min Act: -0.0001

Data Index: 1225253 (C4 (Web Text))

Max Activating Token Index: 237

Text #2

Max Range: 1.1297. Min Range: -1.1297

Max Act: 0.9046. Min Act: -0.0001

Data Index: 1260396 (C4 (Web Text))

Max Activating Token Index: 360

Text #3

Max Range: 1.1297. Min Range: -1.1297

Max Act: 0.8026. Min Act: -0.0001

Data Index: 560421 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 1.1297. Min Range: -1.1297

Max Act: 0.9148. Min Act: -0.0001

Data Index: 861751 (C4 (Web Text))

Max Activating Token Index: 792

Text #5

Max Range: 1.1297. Min Range: -1.1297

Max Act: 0.8720. Min Act: -0.0001

Data Index: 10147 (C4 (Web Text))

Max Activating Token Index: 371

Text #6

Max Range: 1.1297. Min Range: -1.1297

Max Act: 0.8386. Min Act: -0.0001

Data Index: 151307 (C4 (Web Text))

Max Activating Token Index: 548

Text #7

Max Range: 1.1297. Min Range: -1.1297

Max Act: 0.8317. Min Act: -0.0001

Data Index: 131231 (C4 (Web Text))

Max Activating Token Index: 69

Text #8

Max Range: 1.1297. Min Range: -1.1297

Max Act: 0.8178. Min Act: -0.0001

Data Index: 1001368 (C4 (Web Text))

Max Activating Token Index: 699

Text #9

Max Range: 1.1297. Min Range: -1.1297

Max Act: 0.8041. Min Act: -0.0001

Data Index: 951337 (C4 (Web Text))

Max Activating Token Index: 453

Text #10

Max Range: 1.1297. Min Range: -1.1297

Max Act: 0.8152. Min Act: -0.0001

Data Index: 709121 (C4 (Web Text))

Max Activating Token Index: 431

Text #11

Max Range: 1.1297. Min Range: -1.1297

Max Act: 0.8016. Min Act: -0.0001

Data Index: 873802 (C4 (Web Text))

Max Activating Token Index: 316

Text #12

Max Range: 1.1297. Min Range: -1.1297

Max Act: 0.8234. Min Act: -0.0001

Data Index: 1030558 (C4 (Web Text))

Max Activating Token Index: 60

Text #13

Max Range: 1.1297. Min Range: -1.1297

Max Act: 0.8002. Min Act: -0.0001

Data Index: 1292558 (C4 (Web Text))

Max Activating Token Index: 72

Text #14

Max Range: 1.1297. Min Range: -1.1297

Max Act: 0.7953. Min Act: -0.0001

Data Index: 449051 (C4 (Web Text))

Max Activating Token Index: 430

Text #15

Max Range: 1.1297. Min Range: -1.1297

Max Act: 0.7530. Min Act: -0.0001

Data Index: 366702 (C4 (Web Text))

Max Activating Token Index: 394

Text #16

Max Range: 1.1297. Min Range: -1.1297

Max Act: 0.8123. Min Act: -0.0001

Data Index: 295333 (C4 (Web Text))

Max Activating Token Index: 614

Text #17

Max Range: 1.1297. Min Range: -1.1297

Max Act: 0.7901. Min Act: -0.0001

Data Index: 103078 (C4 (Web Text))

Max Activating Token Index: 47

Text #18

Max Range: 1.1297. Min Range: -1.1297

Max Act: 0.7417. Min Act: -0.0001

Data Index: 982795 (C4 (Web Text))

Max Activating Token Index: 452

Text #19

Max Range: 1.1297. Min Range: -1.1297

Max Act: 0.7846. Min Act: -0.0001

Data Index: 241569 (C4 (Web Text))

Max Activating Token Index: 34