Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3613 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.0509. Min Range: -5.0509

Max Act: 5.0509. Min Act: -0.0000

Data Index: 640341 (C4 (Web Text))

Max Activating Token Index: 686

Text #1

Max Range: 5.0509. Min Range: -5.0509

Max Act: 4.8279. Min Act: -0.0000

Data Index: 409631 (C4 (Web Text))

Max Activating Token Index: 385

Text #2

Max Range: 5.0509. Min Range: -5.0509

Max Act: 4.2170. Min Act: -0.0000

Data Index: 583890 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 5.0509. Min Range: -5.0509

Max Act: 4.1076. Min Act: -0.0000

Data Index: 426431 (C4 (Web Text))

Max Activating Token Index: 682

Text #4

Max Range: 5.0509. Min Range: -5.0509

Max Act: 4.1154. Min Act: -0.0000

Data Index: 15858 (C4 (Web Text))

Max Activating Token Index: 722

Text #5

Max Range: 5.0509. Min Range: -5.0509

Max Act: 4.2840. Min Act: -0.0000

Data Index: 364538 (C4 (Web Text))

Max Activating Token Index: 699

Text #6

Max Range: 5.0509. Min Range: -5.0509

Max Act: 3.9750. Min Act: -0.0000

Data Index: 233648 (C4 (Web Text))

Max Activating Token Index: 673

Text #7

Max Range: 5.0509. Min Range: -5.0509

Max Act: 3.8615. Min Act: -0.0000

Data Index: 82225 (C4 (Web Text))

Max Activating Token Index: 315

Text #8

Max Range: 5.0509. Min Range: -5.0509

Max Act: 3.7698. Min Act: -0.0000

Data Index: 1168630 (C4 (Web Text))

Max Activating Token Index: 173

Text #9

Max Range: 5.0509. Min Range: -5.0509

Max Act: 3.7845. Min Act: -0.0000

Data Index: 1107036 (C4 (Web Text))

Max Activating Token Index: 174

Text #10

Max Range: 5.0509. Min Range: -5.0509

Max Act: 3.7299. Min Act: -0.0000

Data Index: 61222 (C4 (Web Text))

Max Activating Token Index: 172

Text #11

Max Range: 5.0509. Min Range: -5.0509

Max Act: 3.5252. Min Act: -0.0000

Data Index: 1354750 (C4 (Web Text))

Max Activating Token Index: 239

Text #12

Max Range: 5.0509. Min Range: -5.0509

Max Act: 3.8232. Min Act: -0.0000

Data Index: 1312134 (C4 (Web Text))

Max Activating Token Index: 577

Text #13

Max Range: 5.0509. Min Range: -5.0509

Max Act: 3.3963. Min Act: -0.0000

Data Index: 429166 (C4 (Web Text))

Max Activating Token Index: 116

Text #14

Max Range: 5.0509. Min Range: -5.0509

Max Act: 3.6997. Min Act: -0.0000

Data Index: 1022761 (C4 (Web Text))

Max Activating Token Index: 968

Text #15

Max Range: 5.0509. Min Range: -5.0509

Max Act: 3.3543. Min Act: -0.0000

Data Index: 1139689 (C4 (Web Text))

Max Activating Token Index: 842

Text #16

Max Range: 5.0509. Min Range: -5.0509

Max Act: 3.4437. Min Act: -0.0000

Data Index: 104991 (C4 (Web Text))

Max Activating Token Index: 395

Text #17

Max Range: 5.0509. Min Range: -5.0509

Max Act: 3.4532. Min Act: -0.0000

Data Index: 365256 (C4 (Web Text))

Max Activating Token Index: 230

Text #18

Max Range: 5.0509. Min Range: -5.0509

Max Act: 3.4290. Min Act: -0.0000

Data Index: 794153 (C4 (Web Text))

Max Activating Token Index: 150

Text #19

Max Range: 5.0509. Min Range: -5.0509

Max Act: 3.3600. Min Act: -0.0000

Data Index: 804773 (C4 (Web Text))

Max Activating Token Index: 38