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

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

Neuron 2456 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.6580. Min Act: -0.0003

Data Index: 883402 (C4 (Web Text))

Max Activating Token Index: 296

Text #1

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.6105. Min Act: -0.0003

Data Index: 1245815 (C4 (Web Text))

Max Activating Token Index: 293

Text #2

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.6009. Min Act: -0.0003

Data Index: 276294 (C4 (Web Text))

Max Activating Token Index: 243

Text #3

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.5929. Min Act: -0.0003

Data Index: 1334277 (C4 (Web Text))

Max Activating Token Index: 114

Text #4

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.5918. Min Act: -0.0003

Data Index: 499757 (C4 (Web Text))

Max Activating Token Index: 61

Text #5

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.5649. Min Act: -0.0002

Data Index: 465303 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.5394. Min Act: -0.0003

Data Index: 313868 (C4 (Web Text))

Max Activating Token Index: 414

Text #7

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.5699. Min Act: -0.0003

Data Index: 436589 (C4 (Web Text))

Max Activating Token Index: 392

Text #8

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.5483. Min Act: -0.0003

Data Index: 855714 (C4 (Web Text))

Max Activating Token Index: 112

Text #9

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.5453. Min Act: -0.0003

Data Index: 1329446 (C4 (Web Text))

Max Activating Token Index: 737

Text #10

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.5445. Min Act: -0.0003

Data Index: 172552 (C4 (Web Text))

Max Activating Token Index: 390

Text #11

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.5397. Min Act: -0.0003

Data Index: 239559 (C4 (Web Text))

Max Activating Token Index: 967

Text #12

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.5353. Min Act: -0.0002

Data Index: 137346 (C4 (Web Text))

Max Activating Token Index: 61

Text #13

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.5194. Min Act: -0.0003

Data Index: 120686 (C4 (Web Text))

Max Activating Token Index: 282

Text #14

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.5322. Min Act: -0.0002

Data Index: 475987 (C4 (Web Text))

Max Activating Token Index: 613

Text #15

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.5296. Min Act: -0.0003

Data Index: 682341 (C4 (Web Text))

Max Activating Token Index: 645

Text #16

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.5130. Min Act: -0.0002

Data Index: 739120 (C4 (Web Text))

Max Activating Token Index: 769

Text #17

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.5283. Min Act: -0.0003

Data Index: 1178686 (C4 (Web Text))

Max Activating Token Index: 171

Text #18

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.5268. Min Act: -0.0003

Data Index: 1265198 (C4 (Web Text))

Max Activating Token Index: 189

Text #19

Max Range: 0.6580. Min Range: -0.6580

Max Act: 0.5184. Min Act: -0.0003

Data Index: 147383 (C4 (Web Text))

Max Activating Token Index: 189