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

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

Neuron 4504 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0573. Min Act: -0.0002

Data Index: 1095456 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0438. Min Act: -0.0003

Data Index: 174326 (C4 (Web Text))

Max Activating Token Index: 922

Text #2

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0452. Min Act: -0.0002

Data Index: 688098 (C4 (Web Text))

Max Activating Token Index: 609

Text #3

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0388. Min Act: -0.0002

Data Index: 1521930 (Python Code)

Max Activating Token Index: 633

Text #4

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0453. Min Act: -0.0002

Data Index: 1356918 (C4 (Web Text))

Max Activating Token Index: 292

Text #5

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0309. Min Act: -0.0002

Data Index: 76419 (C4 (Web Text))

Max Activating Token Index: 600

Text #6

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0359. Min Act: -0.0002

Data Index: 497967 (C4 (Web Text))

Max Activating Token Index: 329

Text #7

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0337. Min Act: -0.0002

Data Index: 1269699 (C4 (Web Text))

Max Activating Token Index: 636

Text #8

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0337. Min Act: -0.0002

Data Index: 36619 (C4 (Web Text))

Max Activating Token Index: 288

Text #9

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0333. Min Act: -0.0002

Data Index: 588383 (C4 (Web Text))

Max Activating Token Index: 259

Text #10

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0304. Min Act: -0.0003

Data Index: 55705 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0333. Min Act: -0.0002

Data Index: 181149 (C4 (Web Text))

Max Activating Token Index: 372

Text #12

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0317. Min Act: -0.0002

Data Index: 923638 (C4 (Web Text))

Max Activating Token Index: 175

Text #13

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0328. Min Act: -0.0003

Data Index: 101271 (C4 (Web Text))

Max Activating Token Index: 77

Text #14

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0311. Min Act: -0.0002

Data Index: 846067 (C4 (Web Text))

Max Activating Token Index: 163

Text #15

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0278. Min Act: -0.0002

Data Index: 1182935 (C4 (Web Text))

Max Activating Token Index: 820

Text #16

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0300. Min Act: -0.0002

Data Index: 112908 (C4 (Web Text))

Max Activating Token Index: 833

Text #17

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0293. Min Act: -0.0002

Data Index: 994696 (C4 (Web Text))

Max Activating Token Index: 97

Text #18

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0262. Min Act: -0.0002

Data Index: 506331 (C4 (Web Text))

Max Activating Token Index: 393

Text #19

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0308. Min Act: -0.0003

Data Index: 1325298 (C4 (Web Text))

Max Activating Token Index: 1023