Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1024 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0364. Min Act: -0.0006

Data Index: 1031165 (C4 (Web Text))

Max Activating Token Index: 824

Text #1

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0321. Min Act: -0.0006

Data Index: 156330 (C4 (Web Text))

Max Activating Token Index: 493

Text #2

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0297. Min Act: -0.0006

Data Index: 642818 (C4 (Web Text))

Max Activating Token Index: 541

Text #3

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0292. Min Act: -0.0006

Data Index: 71118 (C4 (Web Text))

Max Activating Token Index: 499

Text #4

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0279. Min Act: -0.0006

Data Index: 208555 (C4 (Web Text))

Max Activating Token Index: 336

Text #5

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0280. Min Act: -0.0006

Data Index: 243348 (C4 (Web Text))

Max Activating Token Index: 805

Text #6

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0282. Min Act: -0.0006

Data Index: 757786 (C4 (Web Text))

Max Activating Token Index: 990

Text #7

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0261. Min Act: -0.0006

Data Index: 138318 (C4 (Web Text))

Max Activating Token Index: 764

Text #8

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0287. Min Act: -0.0006

Data Index: 1351348 (C4 (Web Text))

Max Activating Token Index: 298

Text #9

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0275. Min Act: -0.0006

Data Index: 1276029 (C4 (Web Text))

Max Activating Token Index: 782

Text #10

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0266. Min Act: -0.0006

Data Index: 1081163 (C4 (Web Text))

Max Activating Token Index: 8

Text #11

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0277. Min Act: -0.0006

Data Index: 788536 (C4 (Web Text))

Max Activating Token Index: 465

Text #12

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0261. Min Act: -0.0006

Data Index: 51065 (C4 (Web Text))

Max Activating Token Index: 843

Text #13

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0271. Min Act: -0.0006

Data Index: 1005242 (C4 (Web Text))

Max Activating Token Index: 895

Text #14

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0253. Min Act: -0.0006

Data Index: 607846 (C4 (Web Text))

Max Activating Token Index: 488

Text #15

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0274. Min Act: -0.0005

Data Index: 1090571 (C4 (Web Text))

Max Activating Token Index: 613

Text #16

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0254. Min Act: -0.0006

Data Index: 1357970 (C4 (Web Text))

Max Activating Token Index: 982

Text #17

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0259. Min Act: -0.0006

Data Index: 1067140 (C4 (Web Text))

Max Activating Token Index: 64

Text #18

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0264. Min Act: -0.0005

Data Index: 1211886 (C4 (Web Text))

Max Activating Token Index: 678

Text #19

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0257. Min Act: -0.0005

Data Index: 1007823 (C4 (Web Text))

Max Activating Token Index: 293