Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1350 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.4264. Min Range: -2.4264

Max Act: 2.4264. Min Act: -0.0000

Data Index: 255187 (C4 (Web Text))

Max Activating Token Index: 916

Text #1

Max Range: 2.4264. Min Range: -2.4264

Max Act: 2.3935. Min Act: -0.0000

Data Index: 1338839 (C4 (Web Text))

Max Activating Token Index: 762

Text #2

Max Range: 2.4264. Min Range: -2.4264

Max Act: 2.0708. Min Act: -0.0000

Data Index: 1045191 (C4 (Web Text))

Max Activating Token Index: 271

Text #3

Max Range: 2.4264. Min Range: -2.4264

Max Act: 2.1771. Min Act: -0.0000

Data Index: 1014667 (C4 (Web Text))

Max Activating Token Index: 432

Text #4

Max Range: 2.4264. Min Range: -2.4264

Max Act: 2.2133. Min Act: -0.0000

Data Index: 512208 (C4 (Web Text))

Max Activating Token Index: 435

Text #5

Max Range: 2.4264. Min Range: -2.4264

Max Act: 2.0778. Min Act: -0.0000

Data Index: 100943 (C4 (Web Text))

Max Activating Token Index: 994

Text #6

Max Range: 2.4264. Min Range: -2.4264

Max Act: 2.0619. Min Act: -0.0000

Data Index: 327193 (C4 (Web Text))

Max Activating Token Index: 317

Text #7

Max Range: 2.4264. Min Range: -2.4264

Max Act: 2.1092. Min Act: -0.0000

Data Index: 1279052 (C4 (Web Text))

Max Activating Token Index: 122

Text #8

Max Range: 2.4264. Min Range: -2.4264

Max Act: 1.9820. Min Act: -0.0000

Data Index: 876717 (C4 (Web Text))

Max Activating Token Index: 490

Text #9

Max Range: 2.4264. Min Range: -2.4264

Max Act: 1.8263. Min Act: -0.0000

Data Index: 668250 (C4 (Web Text))

Max Activating Token Index: 341

Text #10

Max Range: 2.4264. Min Range: -2.4264

Max Act: 1.8107. Min Act: -0.0000

Data Index: 1397950 (Python Code)

Max Activating Token Index: 949

Text #11

Max Range: 2.4264. Min Range: -2.4264

Max Act: 1.6735. Min Act: -0.0000

Data Index: 1219523 (C4 (Web Text))

Max Activating Token Index: 301

Text #12

Max Range: 2.4264. Min Range: -2.4264

Max Act: 1.9123. Min Act: -0.0000

Data Index: 543330 (C4 (Web Text))

Max Activating Token Index: 500

Text #13

Max Range: 2.4264. Min Range: -2.4264

Max Act: 1.6989. Min Act: -0.0000

Data Index: 175779 (C4 (Web Text))

Max Activating Token Index: 944

Text #14

Max Range: 2.4264. Min Range: -2.4264

Max Act: 1.8595. Min Act: -0.0000

Data Index: 1108893 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 2.4264. Min Range: -2.4264

Max Act: 1.8359. Min Act: -0.0000

Data Index: 584368 (C4 (Web Text))

Max Activating Token Index: 957

Text #16

Max Range: 2.4264. Min Range: -2.4264

Max Act: 1.8445. Min Act: -0.0000

Data Index: 750873 (C4 (Web Text))

Max Activating Token Index: 118

Text #17

Max Range: 2.4264. Min Range: -2.4264

Max Act: 1.8359. Min Act: -0.0000

Data Index: 1038949 (C4 (Web Text))

Max Activating Token Index: 399

Text #18

Max Range: 2.4264. Min Range: -2.4264

Max Act: 1.8384. Min Act: -0.0000

Data Index: 770953 (C4 (Web Text))

Max Activating Token Index: 281

Text #19

Max Range: 2.4264. Min Range: -2.4264

Max Act: 1.8196. Min Act: -0.0000

Data Index: 207868 (C4 (Web Text))

Max Activating Token Index: 247