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

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

Neuron 5089 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2982. Min Range: -0.2982

Max Act: 0.2925. Min Act: -0.0000

Data Index: 47687 (C4 (Web Text))

Max Activating Token Index: 401

Text #1

Max Range: 0.2982. Min Range: -0.2982

Max Act: 0.2787. Min Act: -0.0000

Data Index: 158717 (C4 (Web Text))

Max Activating Token Index: 593

Text #2

Max Range: 0.2982. Min Range: -0.2982

Max Act: 0.2982. Min Act: -0.0000

Data Index: 182004 (C4 (Web Text))

Max Activating Token Index: 315

Text #3

Max Range: 0.2982. Min Range: -0.2982

Max Act: 0.2334. Min Act: -0.0000

Data Index: 1150170 (C4 (Web Text))

Max Activating Token Index: 136

Text #4

Max Range: 0.2982. Min Range: -0.2982

Max Act: 0.2534. Min Act: -0.0000

Data Index: 963890 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 0.2982. Min Range: -0.2982

Max Act: 0.2430. Min Act: -0.0000

Data Index: 1254735 (C4 (Web Text))

Max Activating Token Index: 623

Text #6

Max Range: 0.2982. Min Range: -0.2982

Max Act: 0.2354. Min Act: -0.0000

Data Index: 483243 (C4 (Web Text))

Max Activating Token Index: 78

Text #7

Max Range: 0.2982. Min Range: -0.2982

Max Act: 0.2364. Min Act: -0.0000

Data Index: 313225 (C4 (Web Text))

Max Activating Token Index: 601

Text #8

Max Range: 0.2982. Min Range: -0.2982

Max Act: 0.2517. Min Act: -0.0000

Data Index: 610676 (C4 (Web Text))

Max Activating Token Index: 721

Text #9

Max Range: 0.2982. Min Range: -0.2982

Max Act: 0.2525. Min Act: -0.0000

Data Index: 1280584 (C4 (Web Text))

Max Activating Token Index: 393

Text #10

Max Range: 0.2982. Min Range: -0.2982

Max Act: 0.2690. Min Act: -0.0000

Data Index: 213085 (C4 (Web Text))

Max Activating Token Index: 252

Text #11

Max Range: 0.2982. Min Range: -0.2982

Max Act: 0.2398. Min Act: -0.0000

Data Index: 982393 (C4 (Web Text))

Max Activating Token Index: 231

Text #12

Max Range: 0.2982. Min Range: -0.2982

Max Act: 0.2269. Min Act: -0.0000

Data Index: 88521 (C4 (Web Text))

Max Activating Token Index: 310

Text #13

Max Range: 0.2982. Min Range: -0.2982

Max Act: 0.2248. Min Act: -0.0000

Data Index: 375210 (C4 (Web Text))

Max Activating Token Index: 472

Text #14

Max Range: 0.2982. Min Range: -0.2982

Max Act: 0.2397. Min Act: -0.0000

Data Index: 194871 (C4 (Web Text))

Max Activating Token Index: 649

Text #15

Max Range: 0.2982. Min Range: -0.2982

Max Act: 0.2325. Min Act: -0.0000

Data Index: 740225 (C4 (Web Text))

Max Activating Token Index: 330

Text #16

Max Range: 0.2982. Min Range: -0.2982

Max Act: 0.2391. Min Act: -0.0000

Data Index: 846510 (C4 (Web Text))

Max Activating Token Index: 215

Text #17

Max Range: 0.2982. Min Range: -0.2982

Max Act: 0.2154. Min Act: -0.0000

Data Index: 556553 (C4 (Web Text))

Max Activating Token Index: 366

Text #18

Max Range: 0.2982. Min Range: -0.2982

Max Act: 0.2329. Min Act: -0.0000

Data Index: 772779 (C4 (Web Text))

Max Activating Token Index: 291

Text #19

Max Range: 0.2982. Min Range: -0.2982

Max Act: 0.2043. Min Act: -0.0000

Data Index: 1357455 (C4 (Web Text))

Max Activating Token Index: 788