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

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

Neuron 227 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: 0.0325. Min Range: -0.0325

Max Act: 0.0318. Min Act: -0.0006

Data Index: 458826 (C4 (Web Text))

Max Activating Token Index: 654

Text #1

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0316. Min Act: -0.0006

Data Index: 1230877 (C4 (Web Text))

Max Activating Token Index: 813

Text #2

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0325. Min Act: -0.0005

Data Index: 609750 (C4 (Web Text))

Max Activating Token Index: 880

Text #3

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0292. Min Act: -0.0005

Data Index: 1069263 (C4 (Web Text))

Max Activating Token Index: 772

Text #4

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0271. Min Act: -0.0006

Data Index: 786064 (C4 (Web Text))

Max Activating Token Index: 201

Text #5

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0272. Min Act: -0.0006

Data Index: 1035085 (C4 (Web Text))

Max Activating Token Index: 139

Text #6

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0260. Min Act: -0.0005

Data Index: 16088 (C4 (Web Text))

Max Activating Token Index: 814

Text #7

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0270. Min Act: -0.0005

Data Index: 756501 (C4 (Web Text))

Max Activating Token Index: 832

Text #8

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0267. Min Act: -0.0006

Data Index: 1002724 (C4 (Web Text))

Max Activating Token Index: 1008

Text #9

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0261. Min Act: -0.0006

Data Index: 87017 (C4 (Web Text))

Max Activating Token Index: 70

Text #10

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0269. Min Act: -0.0006

Data Index: 907551 (C4 (Web Text))

Max Activating Token Index: 251

Text #11

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0268. Min Act: -0.0006

Data Index: 476455 (C4 (Web Text))

Max Activating Token Index: 619

Text #12

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0251. Min Act: -0.0006

Data Index: 408351 (C4 (Web Text))

Max Activating Token Index: 661

Text #13

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0254. Min Act: -0.0006

Data Index: 1064226 (C4 (Web Text))

Max Activating Token Index: 738

Text #14

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0254. Min Act: -0.0006

Data Index: 1012401 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0246. Min Act: -0.0005

Data Index: 470032 (C4 (Web Text))

Max Activating Token Index: 364

Text #16

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0247. Min Act: -0.0006

Data Index: 716171 (C4 (Web Text))

Max Activating Token Index: 818

Text #17

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0245. Min Act: -0.0006

Data Index: 947857 (C4 (Web Text))

Max Activating Token Index: 426

Text #18

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0245. Min Act: -0.0006

Data Index: 1087952 (C4 (Web Text))

Max Activating Token Index: 906

Text #19

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0233. Min Act: -0.0006

Data Index: 672719 (C4 (Web Text))

Max Activating Token Index: 967