Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 844 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.5470. Min Range: -1.5470

Max Act: 1.5117. Min Act: -0.0001

Data Index: 643800 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 1.5470. Min Range: -1.5470

Max Act: 1.5000. Min Act: -0.0001

Data Index: 241122 (C4 (Web Text))

Max Activating Token Index: 239

Text #2

Max Range: 1.5470. Min Range: -1.5470

Max Act: 1.5470. Min Act: -0.0001

Data Index: 700326 (C4 (Web Text))

Max Activating Token Index: 299

Text #3

Max Range: 1.5470. Min Range: -1.5470

Max Act: 1.3588. Min Act: -0.0001

Data Index: 1128408 (C4 (Web Text))

Max Activating Token Index: 281

Text #4

Max Range: 1.5470. Min Range: -1.5470

Max Act: 1.1911. Min Act: -0.0001

Data Index: 1302637 (C4 (Web Text))

Max Activating Token Index: 70

Text #5

Max Range: 1.5470. Min Range: -1.5470

Max Act: 1.1469. Min Act: -0.0001

Data Index: 1331252 (C4 (Web Text))

Max Activating Token Index: 392

Text #6

Max Range: 1.5470. Min Range: -1.5470

Max Act: 1.1203. Min Act: -0.0001

Data Index: 645179 (C4 (Web Text))

Max Activating Token Index: 766

Text #7

Max Range: 1.5470. Min Range: -1.5470

Max Act: 1.0116. Min Act: -0.0001

Data Index: 1354283 (C4 (Web Text))

Max Activating Token Index: 372

Text #8

Max Range: 1.5470. Min Range: -1.5470

Max Act: 1.1097. Min Act: -0.0001

Data Index: 126202 (C4 (Web Text))

Max Activating Token Index: 454

Text #9

Max Range: 1.5470. Min Range: -1.5470

Max Act: 1.0354. Min Act: -0.0001

Data Index: 516312 (C4 (Web Text))

Max Activating Token Index: 494

Text #10

Max Range: 1.5470. Min Range: -1.5470

Max Act: 0.9972. Min Act: -0.0001

Data Index: 662310 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 1.5470. Min Range: -1.5470

Max Act: 0.9281. Min Act: -0.0001

Data Index: 1175924 (C4 (Web Text))

Max Activating Token Index: 376

Text #12

Max Range: 1.5470. Min Range: -1.5470

Max Act: 0.9648. Min Act: -0.0001

Data Index: 790952 (C4 (Web Text))

Max Activating Token Index: 236

Text #13

Max Range: 1.5470. Min Range: -1.5470

Max Act: 0.9639. Min Act: -0.0001

Data Index: 496828 (C4 (Web Text))

Max Activating Token Index: 352

Text #14

Max Range: 1.5470. Min Range: -1.5470

Max Act: 0.9234. Min Act: -0.0001

Data Index: 1202743 (C4 (Web Text))

Max Activating Token Index: 152

Text #15

Max Range: 1.5470. Min Range: -1.5470

Max Act: 0.9341. Min Act: -0.0001

Data Index: 774838 (C4 (Web Text))

Max Activating Token Index: 318

Text #16

Max Range: 1.5470. Min Range: -1.5470

Max Act: 0.9277. Min Act: -0.0001

Data Index: 1108339 (C4 (Web Text))

Max Activating Token Index: 699

Text #17

Max Range: 1.5470. Min Range: -1.5470

Max Act: 0.8911. Min Act: -0.0001

Data Index: 715057 (C4 (Web Text))

Max Activating Token Index: 211

Text #18

Max Range: 1.5470. Min Range: -1.5470

Max Act: 0.9185. Min Act: -0.0001

Data Index: 260117 (C4 (Web Text))

Max Activating Token Index: 279

Text #19

Max Range: 1.5470. Min Range: -1.5470

Max Act: 0.8891. Min Act: -0.0001

Data Index: 1213905 (C4 (Web Text))

Max Activating Token Index: 42