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

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

Neuron 3441 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.3344. Min Act: -0.0000

Data Index: 543233 (C4 (Web Text))

Max Activating Token Index: 471

Text #1

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.2863. Min Act: -0.0000

Data Index: 305414 (C4 (Web Text))

Max Activating Token Index: 875

Text #2

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.2722. Min Act: -0.0000

Data Index: 743149 (C4 (Web Text))

Max Activating Token Index: 567

Text #3

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.2437. Min Act: -0.0000

Data Index: 362133 (C4 (Web Text))

Max Activating Token Index: 839

Text #4

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.2753. Min Act: -0.0000

Data Index: 1225029 (C4 (Web Text))

Max Activating Token Index: 437

Text #5

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.2526. Min Act: -0.0000

Data Index: 862010 (C4 (Web Text))

Max Activating Token Index: 983

Text #6

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.2506. Min Act: 0.0001

Data Index: 778220 (C4 (Web Text))

Max Activating Token Index: 943

Text #7

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.2490. Min Act: -0.0000

Data Index: 919083 (C4 (Web Text))

Max Activating Token Index: 532

Text #8

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.2614. Min Act: -0.0000

Data Index: 1440547 (Python Code)

Max Activating Token Index: 301

Text #9

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.2341. Min Act: 0.0000

Data Index: 1099545 (C4 (Web Text))

Max Activating Token Index: 562

Text #10

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.2318. Min Act: -0.0000

Data Index: 200197 (C4 (Web Text))

Max Activating Token Index: 231

Text #11

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.2366. Min Act: -0.0000

Data Index: 425348 (C4 (Web Text))

Max Activating Token Index: 1022

Text #12

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.2348. Min Act: -0.0000

Data Index: 733355 (C4 (Web Text))

Max Activating Token Index: 87

Text #13

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.2150. Min Act: -0.0000

Data Index: 1221754 (C4 (Web Text))

Max Activating Token Index: 917

Text #14

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.2343. Min Act: -0.0000

Data Index: 651464 (C4 (Web Text))

Max Activating Token Index: 844

Text #15

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.2159. Min Act: -0.0000

Data Index: 740235 (C4 (Web Text))

Max Activating Token Index: 327

Text #16

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.2139. Min Act: -0.0000

Data Index: 963377 (C4 (Web Text))

Max Activating Token Index: 764

Text #17

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.2110. Min Act: -0.0000

Data Index: 1061465 (C4 (Web Text))

Max Activating Token Index: 357

Text #18

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.2054. Min Act: 0.0000

Data Index: 1229809 (C4 (Web Text))

Max Activating Token Index: 243

Text #19

Max Range: 0.3344. Min Range: -0.3344

Max Act: 0.2022. Min Act: -0.0000

Data Index: 1091160 (C4 (Web Text))

Max Activating Token Index: 719