Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1504 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0295. Min Act: -0.0006

Data Index: 67445 (C4 (Web Text))

Max Activating Token Index: 675

Text #1

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0291. Min Act: -0.0006

Data Index: 55480 (C4 (Web Text))

Max Activating Token Index: 278

Text #2

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0295. Min Act: -0.0006

Data Index: 1138172 (C4 (Web Text))

Max Activating Token Index: 161

Text #3

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0282. Min Act: -0.0006

Data Index: 1100446 (C4 (Web Text))

Max Activating Token Index: 349

Text #4

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0281. Min Act: -0.0006

Data Index: 919045 (C4 (Web Text))

Max Activating Token Index: 585

Text #5

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0285. Min Act: -0.0006

Data Index: 440760 (C4 (Web Text))

Max Activating Token Index: 389

Text #6

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0286. Min Act: -0.0006

Data Index: 114178 (C4 (Web Text))

Max Activating Token Index: 139

Text #7

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0280. Min Act: -0.0006

Data Index: 365932 (C4 (Web Text))

Max Activating Token Index: 546

Text #8

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0271. Min Act: -0.0006

Data Index: 314990 (C4 (Web Text))

Max Activating Token Index: 768

Text #9

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0287. Min Act: -0.0006

Data Index: 1089376 (C4 (Web Text))

Max Activating Token Index: 897

Text #10

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0275. Min Act: -0.0006

Data Index: 1291883 (C4 (Web Text))

Max Activating Token Index: 207

Text #11

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0281. Min Act: -0.0006

Data Index: 1138270 (C4 (Web Text))

Max Activating Token Index: 192

Text #12

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0280. Min Act: -0.0006

Data Index: 833231 (C4 (Web Text))

Max Activating Token Index: 914

Text #13

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0280. Min Act: -0.0006

Data Index: 1331455 (C4 (Web Text))

Max Activating Token Index: 405

Text #14

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0271. Min Act: -0.0006

Data Index: 48966 (C4 (Web Text))

Max Activating Token Index: 340

Text #15

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0285. Min Act: -0.0006

Data Index: 1332574 (C4 (Web Text))

Max Activating Token Index: 563

Text #16

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0279. Min Act: -0.0006

Data Index: 99166 (C4 (Web Text))

Max Activating Token Index: 325

Text #17

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0283. Min Act: -0.0006

Data Index: 1297183 (C4 (Web Text))

Max Activating Token Index: 568

Text #18

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0282. Min Act: -0.0006

Data Index: 1296649 (C4 (Web Text))

Max Activating Token Index: 521

Text #19

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0281. Min Act: -0.0006

Data Index: 226214 (C4 (Web Text))

Max Activating Token Index: 23