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

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

Neuron 4090 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.3138. Min Act: -0.0001

Data Index: 868038 (C4 (Web Text))

Max Activating Token Index: 196

Text #1

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2686. Min Act: -0.0001

Data Index: 56644 (C4 (Web Text))

Max Activating Token Index: 873

Text #2

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2784. Min Act: -0.0001

Data Index: 1357159 (C4 (Web Text))

Max Activating Token Index: 466

Text #3

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2748. Min Act: -0.0000

Data Index: 1218290 (C4 (Web Text))

Max Activating Token Index: 179

Text #4

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2736. Min Act: -0.0001

Data Index: 468168 (C4 (Web Text))

Max Activating Token Index: 260

Text #5

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2771. Min Act: -0.0001

Data Index: 918711 (C4 (Web Text))

Max Activating Token Index: 513

Text #6

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2449. Min Act: -0.0000

Data Index: 823142 (C4 (Web Text))

Max Activating Token Index: 340

Text #7

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2554. Min Act: -0.0000

Data Index: 1105227 (C4 (Web Text))

Max Activating Token Index: 152

Text #8

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2532. Min Act: -0.0000

Data Index: 524426 (C4 (Web Text))

Max Activating Token Index: 505

Text #9

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2437. Min Act: -0.0001

Data Index: 59617 (C4 (Web Text))

Max Activating Token Index: 459

Text #10

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2277. Min Act: -0.0001

Data Index: 885407 (C4 (Web Text))

Max Activating Token Index: 762

Text #11

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2558. Min Act: -0.0001

Data Index: 889132 (C4 (Web Text))

Max Activating Token Index: 596

Text #12

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2232. Min Act: -0.0001

Data Index: 1521868 (Python Code)

Max Activating Token Index: 629

Text #13

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2284. Min Act: -0.0001

Data Index: 1268362 (C4 (Web Text))

Max Activating Token Index: 686

Text #14

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2299. Min Act: -0.0001

Data Index: 416327 (C4 (Web Text))

Max Activating Token Index: 532

Text #15

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2289. Min Act: -0.0000

Data Index: 477412 (C4 (Web Text))

Max Activating Token Index: 558

Text #16

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2363. Min Act: -0.0001

Data Index: 983169 (C4 (Web Text))

Max Activating Token Index: 1013

Text #17

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2484. Min Act: -0.0001

Data Index: 223973 (C4 (Web Text))

Max Activating Token Index: 155

Text #18

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2343. Min Act: -0.0001

Data Index: 196210 (C4 (Web Text))

Max Activating Token Index: 844

Text #19

Max Range: 0.3138. Min Range: -0.3138

Max Act: 0.2212. Min Act: -0.0001

Data Index: 707420 (C4 (Web Text))

Max Activating Token Index: 785