Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 995 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0398. Min Act: -0.0005

Data Index: 764423 (C4 (Web Text))

Max Activating Token Index: 591

Text #1

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0402. Min Act: -0.0005

Data Index: 209182 (C4 (Web Text))

Max Activating Token Index: 203

Text #2

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0368. Min Act: -0.0005

Data Index: 1013850 (C4 (Web Text))

Max Activating Token Index: 357

Text #3

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0368. Min Act: -0.0006

Data Index: 805376 (C4 (Web Text))

Max Activating Token Index: 637

Text #4

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0337. Min Act: -0.0006

Data Index: 480192 (C4 (Web Text))

Max Activating Token Index: 248

Text #5

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0330. Min Act: -0.0005

Data Index: 251629 (C4 (Web Text))

Max Activating Token Index: 973

Text #6

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0313. Min Act: -0.0005

Data Index: 1167172 (C4 (Web Text))

Max Activating Token Index: 673

Text #7

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0315. Min Act: -0.0005

Data Index: 985648 (C4 (Web Text))

Max Activating Token Index: 644

Text #8

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0315. Min Act: -0.0006

Data Index: 322721 (C4 (Web Text))

Max Activating Token Index: 662

Text #9

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0298. Min Act: -0.0006

Data Index: 957166 (C4 (Web Text))

Max Activating Token Index: 917

Text #10

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0301. Min Act: -0.0006

Data Index: 433051 (C4 (Web Text))

Max Activating Token Index: 784

Text #11

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0290. Min Act: -0.0005

Data Index: 1505139 (Python Code)

Max Activating Token Index: 288

Text #12

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0286. Min Act: -0.0005

Data Index: 1448976 (Python Code)

Max Activating Token Index: 385

Text #13

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0285. Min Act: -0.0005

Data Index: 1559092 (Python Code)

Max Activating Token Index: 714

Text #14

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0277. Min Act: -0.0006

Data Index: 808868 (C4 (Web Text))

Max Activating Token Index: 281

Text #15

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0275. Min Act: -0.0005

Data Index: 1594742 (Python Code)

Max Activating Token Index: 982

Text #16

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0277. Min Act: -0.0005

Data Index: 1538836 (Python Code)

Max Activating Token Index: 243

Text #17

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0275. Min Act: -0.0005

Data Index: 1094499 (C4 (Web Text))

Max Activating Token Index: 685

Text #18

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0281. Min Act: -0.0005

Data Index: 1577068 (Python Code)

Max Activating Token Index: 949

Text #19

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0273. Min Act: -0.0006

Data Index: 991381 (C4 (Web Text))

Max Activating Token Index: 480