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

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

Neuron 2711 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.3179. Min Act: -0.0000

Data Index: 1257229 (C4 (Web Text))

Max Activating Token Index: 627

Text #1

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.2934. Min Act: -0.0000

Data Index: 666133 (C4 (Web Text))

Max Activating Token Index: 793

Text #2

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.2824. Min Act: -0.0000

Data Index: 545928 (C4 (Web Text))

Max Activating Token Index: 772

Text #3

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.3017. Min Act: -0.0000

Data Index: 1185122 (C4 (Web Text))

Max Activating Token Index: 381

Text #4

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.2741. Min Act: -0.0000

Data Index: 1303391 (C4 (Web Text))

Max Activating Token Index: 341

Text #5

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.2614. Min Act: -0.0000

Data Index: 1292281 (C4 (Web Text))

Max Activating Token Index: 248

Text #6

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.2427. Min Act: -0.0000

Data Index: 733742 (C4 (Web Text))

Max Activating Token Index: 248

Text #7

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.2401. Min Act: -0.0000

Data Index: 960865 (C4 (Web Text))

Max Activating Token Index: 504

Text #8

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.2463. Min Act: -0.0000

Data Index: 199550 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.2400. Min Act: -0.0000

Data Index: 612558 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.2441. Min Act: -0.0000

Data Index: 267275 (C4 (Web Text))

Max Activating Token Index: 1004

Text #11

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.2270. Min Act: -0.0000

Data Index: 736194 (C4 (Web Text))

Max Activating Token Index: 827

Text #12

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.2346. Min Act: -0.0000

Data Index: 78370 (C4 (Web Text))

Max Activating Token Index: 34

Text #13

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.2207. Min Act: -0.0000

Data Index: 954294 (C4 (Web Text))

Max Activating Token Index: 391

Text #14

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.2395. Min Act: -0.0000

Data Index: 342157 (C4 (Web Text))

Max Activating Token Index: 749

Text #15

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.2461. Min Act: -0.0000

Data Index: 977123 (C4 (Web Text))

Max Activating Token Index: 955

Text #16

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.2359. Min Act: -0.0000

Data Index: 391880 (C4 (Web Text))

Max Activating Token Index: 839

Text #17

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.2306. Min Act: -0.0000

Data Index: 527207 (C4 (Web Text))

Max Activating Token Index: 609

Text #18

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.2315. Min Act: -0.0000

Data Index: 935264 (C4 (Web Text))

Max Activating Token Index: 895

Text #19

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.2313. Min Act: -0.0000

Data Index: 461155 (C4 (Web Text))

Max Activating Token Index: 433