Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2726 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5372. Min Range: -1.5372

Max Act: 1.5372. Min Act: -0.0000

Data Index: 430944 (C4 (Web Text))

Max Activating Token Index: 221

Text #1

Max Range: 1.5372. Min Range: -1.5372

Max Act: 1.1599. Min Act: -0.0001

Data Index: 573350 (C4 (Web Text))

Max Activating Token Index: 197

Text #2

Max Range: 1.5372. Min Range: -1.5372

Max Act: 0.9879. Min Act: -0.0000

Data Index: 520471 (C4 (Web Text))

Max Activating Token Index: 275

Text #3

Max Range: 1.5372. Min Range: -1.5372

Max Act: 0.9716. Min Act: -0.0001

Data Index: 24560 (C4 (Web Text))

Max Activating Token Index: 314

Text #4

Max Range: 1.5372. Min Range: -1.5372

Max Act: 0.9403. Min Act: -0.0000

Data Index: 1282405 (C4 (Web Text))

Max Activating Token Index: 336

Text #5

Max Range: 1.5372. Min Range: -1.5372

Max Act: 0.9195. Min Act: -0.0000

Data Index: 134839 (C4 (Web Text))

Max Activating Token Index: 205

Text #6

Max Range: 1.5372. Min Range: -1.5372

Max Act: 0.8815. Min Act: -0.0000

Data Index: 156331 (C4 (Web Text))

Max Activating Token Index: 741

Text #7

Max Range: 1.5372. Min Range: -1.5372

Max Act: 0.8819. Min Act: -0.0000

Data Index: 46420 (C4 (Web Text))

Max Activating Token Index: 439

Text #8

Max Range: 1.5372. Min Range: -1.5372

Max Act: 0.8415. Min Act: -0.0001

Data Index: 773712 (C4 (Web Text))

Max Activating Token Index: 585

Text #9

Max Range: 1.5372. Min Range: -1.5372

Max Act: 0.8258. Min Act: -0.0000

Data Index: 204874 (C4 (Web Text))

Max Activating Token Index: 26

Text #10

Max Range: 1.5372. Min Range: -1.5372

Max Act: 0.8382. Min Act: -0.0000

Data Index: 458352 (C4 (Web Text))

Max Activating Token Index: 398

Text #11

Max Range: 1.5372. Min Range: -1.5372

Max Act: 0.8089. Min Act: -0.0000

Data Index: 489281 (C4 (Web Text))

Max Activating Token Index: 265

Text #12

Max Range: 1.5372. Min Range: -1.5372

Max Act: 0.8543. Min Act: -0.0000

Data Index: 768743 (C4 (Web Text))

Max Activating Token Index: 557

Text #13

Max Range: 1.5372. Min Range: -1.5372

Max Act: 0.8017. Min Act: -0.0000

Data Index: 385038 (C4 (Web Text))

Max Activating Token Index: 233

Text #14

Max Range: 1.5372. Min Range: -1.5372

Max Act: 0.8171. Min Act: -0.0000

Data Index: 752084 (C4 (Web Text))

Max Activating Token Index: 251

Text #15

Max Range: 1.5372. Min Range: -1.5372

Max Act: 0.7534. Min Act: -0.0000

Data Index: 137005 (C4 (Web Text))

Max Activating Token Index: 67

Text #16

Max Range: 1.5372. Min Range: -1.5372

Max Act: 0.7966. Min Act: -0.0000

Data Index: 76815 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 1.5372. Min Range: -1.5372

Max Act: 0.7647. Min Act: -0.0000

Data Index: 363591 (C4 (Web Text))

Max Activating Token Index: 577

Text #18

Max Range: 1.5372. Min Range: -1.5372

Max Act: 0.7436. Min Act: -0.0001

Data Index: 196363 (C4 (Web Text))

Max Activating Token Index: 940

Text #19

Max Range: 1.5372. Min Range: -1.5372

Max Act: 0.7614. Min Act: -0.0000

Data Index: 19146 (C4 (Web Text))

Max Activating Token Index: 204