Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2558 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.5067. Min Act: -0.0000

Data Index: 202578 (C4 (Web Text))

Max Activating Token Index: 260

Text #1

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.4342. Min Act: -0.0000

Data Index: 667377 (C4 (Web Text))

Max Activating Token Index: 934

Text #2

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.4469. Min Act: -0.0000

Data Index: 486234 (C4 (Web Text))

Max Activating Token Index: 607

Text #3

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.4185. Min Act: -0.0000

Data Index: 836063 (C4 (Web Text))

Max Activating Token Index: 763

Text #4

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.4032. Min Act: -0.0000

Data Index: 437775 (C4 (Web Text))

Max Activating Token Index: 241

Text #5

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.4182. Min Act: -0.0000

Data Index: 1318965 (C4 (Web Text))

Max Activating Token Index: 162

Text #6

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.4282. Min Act: -0.0000

Data Index: 226621 (C4 (Web Text))

Max Activating Token Index: 267

Text #7

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.4100. Min Act: -0.0000

Data Index: 1118652 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.4357. Min Act: -0.0000

Data Index: 1359100 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.4146. Min Act: -0.0000

Data Index: 1130243 (C4 (Web Text))

Max Activating Token Index: 792

Text #10

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.4003. Min Act: -0.0000

Data Index: 132744 (C4 (Web Text))

Max Activating Token Index: 351

Text #11

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.3760. Min Act: -0.0000

Data Index: 327822 (C4 (Web Text))

Max Activating Token Index: 632

Text #12

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.3907. Min Act: -0.0000

Data Index: 629969 (C4 (Web Text))

Max Activating Token Index: 973

Text #13

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.3866. Min Act: -0.0000

Data Index: 260159 (C4 (Web Text))

Max Activating Token Index: 388

Text #14

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.3648. Min Act: -0.0000

Data Index: 515988 (C4 (Web Text))

Max Activating Token Index: 180

Text #15

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.3664. Min Act: -0.0000

Data Index: 19710 (C4 (Web Text))

Max Activating Token Index: 259

Text #16

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.3808. Min Act: -0.0000

Data Index: 106248 (C4 (Web Text))

Max Activating Token Index: 186

Text #17

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.3766. Min Act: -0.0000

Data Index: 429178 (C4 (Web Text))

Max Activating Token Index: 541

Text #18

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.3727. Min Act: -0.0000

Data Index: 870725 (C4 (Web Text))

Max Activating Token Index: 395

Text #19

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.3558. Min Act: -0.0000

Data Index: 600199 (C4 (Web Text))

Max Activating Token Index: 1014