Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1293 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0305. Min Act: -0.0006

Data Index: 627611 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0276. Min Act: -0.0006

Data Index: 495487 (C4 (Web Text))

Max Activating Token Index: 40

Text #2

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0277. Min Act: -0.0006

Data Index: 1287021 (C4 (Web Text))

Max Activating Token Index: 873

Text #3

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0269. Min Act: -0.0005

Data Index: 226289 (C4 (Web Text))

Max Activating Token Index: 94

Text #4

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0255. Min Act: -0.0005

Data Index: 156020 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0255. Min Act: -0.0006

Data Index: 558118 (C4 (Web Text))

Max Activating Token Index: 17

Text #6

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0263. Min Act: -0.0006

Data Index: 783942 (C4 (Web Text))

Max Activating Token Index: 410

Text #7

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0249. Min Act: -0.0006

Data Index: 1455274 (Python Code)

Max Activating Token Index: 808

Text #8

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0253. Min Act: -0.0006

Data Index: 1235082 (C4 (Web Text))

Max Activating Token Index: 504

Text #9

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0241. Min Act: -0.0006

Data Index: 588599 (C4 (Web Text))

Max Activating Token Index: 582

Text #10

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0250. Min Act: -0.0006

Data Index: 1166865 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0238. Min Act: -0.0006

Data Index: 53972 (C4 (Web Text))

Max Activating Token Index: 165

Text #12

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0246. Min Act: -0.0006

Data Index: 218786 (C4 (Web Text))

Max Activating Token Index: 776

Text #13

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0238. Min Act: -0.0005

Data Index: 433693 (C4 (Web Text))

Max Activating Token Index: 336

Text #14

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0237. Min Act: -0.0005

Data Index: 1315454 (C4 (Web Text))

Max Activating Token Index: 253

Text #15

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0248. Min Act: -0.0006

Data Index: 1415056 (Python Code)

Max Activating Token Index: 114

Text #16

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0235. Min Act: -0.0006

Data Index: 118244 (C4 (Web Text))

Max Activating Token Index: 827

Text #17

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0232. Min Act: -0.0006

Data Index: 904910 (C4 (Web Text))

Max Activating Token Index: 695

Text #18

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0243. Min Act: -0.0006

Data Index: 540307 (C4 (Web Text))

Max Activating Token Index: 288

Text #19

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0229. Min Act: -0.0006

Data Index: 1484477 (Python Code)

Max Activating Token Index: 601