Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2411 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3331. Min Range: -0.3331

Max Act: 0.3331. Min Act: -0.0001

Data Index: 104471 (C4 (Web Text))

Max Activating Token Index: 386

Text #1

Max Range: 0.3331. Min Range: -0.3331

Max Act: 0.2914. Min Act: -0.0001

Data Index: 382680 (C4 (Web Text))

Max Activating Token Index: 248

Text #2

Max Range: 0.3331. Min Range: -0.3331

Max Act: 0.2554. Min Act: -0.0001

Data Index: 663455 (C4 (Web Text))

Max Activating Token Index: 360

Text #3

Max Range: 0.3331. Min Range: -0.3331

Max Act: 0.2618. Min Act: -0.0001

Data Index: 1100302 (C4 (Web Text))

Max Activating Token Index: 973

Text #4

Max Range: 0.3331. Min Range: -0.3331

Max Act: 0.2395. Min Act: -0.0001

Data Index: 1165692 (C4 (Web Text))

Max Activating Token Index: 334

Text #5

Max Range: 0.3331. Min Range: -0.3331

Max Act: 0.2398. Min Act: -0.0001

Data Index: 459291 (C4 (Web Text))

Max Activating Token Index: 513

Text #6

Max Range: 0.3331. Min Range: -0.3331

Max Act: 0.2331. Min Act: -0.0001

Data Index: 652501 (C4 (Web Text))

Max Activating Token Index: 726

Text #7

Max Range: 0.3331. Min Range: -0.3331

Max Act: 0.2381. Min Act: -0.0001

Data Index: 1213978 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 0.3331. Min Range: -0.3331

Max Act: 0.2380. Min Act: -0.0001

Data Index: 1099476 (C4 (Web Text))

Max Activating Token Index: 334

Text #9

Max Range: 0.3331. Min Range: -0.3331

Max Act: 0.2198. Min Act: -0.0001

Data Index: 1004083 (C4 (Web Text))

Max Activating Token Index: 681

Text #10

Max Range: 0.3331. Min Range: -0.3331

Max Act: 0.2053. Min Act: -0.0001

Data Index: 619038 (C4 (Web Text))

Max Activating Token Index: 636

Text #11

Max Range: 0.3331. Min Range: -0.3331

Max Act: 0.2215. Min Act: -0.0001

Data Index: 36619 (C4 (Web Text))

Max Activating Token Index: 288

Text #12

Max Range: 0.3331. Min Range: -0.3331

Max Act: 0.2216. Min Act: -0.0001

Data Index: 462676 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 0.3331. Min Range: -0.3331

Max Act: 0.2301. Min Act: -0.0001

Data Index: 581766 (C4 (Web Text))

Max Activating Token Index: 6

Text #14

Max Range: 0.3331. Min Range: -0.3331

Max Act: 0.2342. Min Act: -0.0001

Data Index: 497967 (C4 (Web Text))

Max Activating Token Index: 328

Text #15

Max Range: 0.3331. Min Range: -0.3331

Max Act: 0.2121. Min Act: -0.0001

Data Index: 532507 (C4 (Web Text))

Max Activating Token Index: 621

Text #16

Max Range: 0.3331. Min Range: -0.3331

Max Act: 0.2408. Min Act: -0.0001

Data Index: 66138 (C4 (Web Text))

Max Activating Token Index: 247

Text #17

Max Range: 0.3331. Min Range: -0.3331

Max Act: 0.2122. Min Act: -0.0001

Data Index: 1053045 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 0.3331. Min Range: -0.3331

Max Act: 0.2086. Min Act: -0.0001

Data Index: 244490 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 0.3331. Min Range: -0.3331

Max Act: 0.2002. Min Act: -0.0001

Data Index: 1009704 (C4 (Web Text))

Max Activating Token Index: 574