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

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

Neuron 4203 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: 0.2815. Min Range: -0.2815

Max Act: 0.2681. Min Act: -0.0002

Data Index: 1063188 (C4 (Web Text))

Max Activating Token Index: 857

Text #1

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2815. Min Act: -0.0002

Data Index: 406961 (C4 (Web Text))

Max Activating Token Index: 779

Text #2

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2603. Min Act: -0.0002

Data Index: 388530 (C4 (Web Text))

Max Activating Token Index: 120

Text #3

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2764. Min Act: -0.0002

Data Index: 741117 (C4 (Web Text))

Max Activating Token Index: 942

Text #4

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2501. Min Act: -0.0002

Data Index: 966607 (C4 (Web Text))

Max Activating Token Index: 120

Text #5

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2463. Min Act: -0.0002

Data Index: 835699 (C4 (Web Text))

Max Activating Token Index: 76

Text #6

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2308. Min Act: -0.0002

Data Index: 134942 (C4 (Web Text))

Max Activating Token Index: 96

Text #7

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2554. Min Act: -0.0002

Data Index: 323404 (C4 (Web Text))

Max Activating Token Index: 269

Text #8

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2425. Min Act: -0.0002

Data Index: 38225 (C4 (Web Text))

Max Activating Token Index: 469

Text #9

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2484. Min Act: -0.0002

Data Index: 1192450 (C4 (Web Text))

Max Activating Token Index: 362

Text #10

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2390. Min Act: -0.0002

Data Index: 567207 (C4 (Web Text))

Max Activating Token Index: 193

Text #11

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2449. Min Act: -0.0002

Data Index: 1014391 (C4 (Web Text))

Max Activating Token Index: 565

Text #12

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2214. Min Act: -0.0002

Data Index: 742654 (C4 (Web Text))

Max Activating Token Index: 172

Text #13

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2338. Min Act: -0.0002

Data Index: 868781 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2409. Min Act: -0.0002

Data Index: 550665 (C4 (Web Text))

Max Activating Token Index: 297

Text #15

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2086. Min Act: -0.0002

Data Index: 73953 (C4 (Web Text))

Max Activating Token Index: 221

Text #16

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2494. Min Act: -0.0002

Data Index: 95555 (C4 (Web Text))

Max Activating Token Index: 42

Text #17

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2391. Min Act: -0.0002

Data Index: 832707 (C4 (Web Text))

Max Activating Token Index: 843

Text #18

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2391. Min Act: -0.0002

Data Index: 14146 (C4 (Web Text))

Max Activating Token Index: 756

Text #19

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2150. Min Act: -0.0002

Data Index: 971351 (C4 (Web Text))

Max Activating Token Index: 158