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

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

Neuron 672 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: 1.9421. Min Range: -1.9421

Max Act: 1.9421. Min Act: -0.0000

Data Index: 1104390 (C4 (Web Text))

Max Activating Token Index: 625

Text #1

Max Range: 1.9421. Min Range: -1.9421

Max Act: 1.6711. Min Act: -0.0000

Data Index: 155063 (C4 (Web Text))

Max Activating Token Index: 240

Text #2

Max Range: 1.9421. Min Range: -1.9421

Max Act: 1.4324. Min Act: -0.0000

Data Index: 716765 (C4 (Web Text))

Max Activating Token Index: 362

Text #3

Max Range: 1.9421. Min Range: -1.9421

Max Act: 1.3273. Min Act: -0.0000

Data Index: 764235 (C4 (Web Text))

Max Activating Token Index: 55

Text #4

Max Range: 1.9421. Min Range: -1.9421

Max Act: 1.3138. Min Act: -0.0000

Data Index: 238614 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 1.9421. Min Range: -1.9421

Max Act: 1.3346. Min Act: -0.0000

Data Index: 539195 (C4 (Web Text))

Max Activating Token Index: 739

Text #6

Max Range: 1.9421. Min Range: -1.9421

Max Act: 1.2467. Min Act: -0.0000

Data Index: 409148 (C4 (Web Text))

Max Activating Token Index: 720

Text #7

Max Range: 1.9421. Min Range: -1.9421

Max Act: 1.2292. Min Act: -0.0000

Data Index: 680734 (C4 (Web Text))

Max Activating Token Index: 739

Text #8

Max Range: 1.9421. Min Range: -1.9421

Max Act: 1.1322. Min Act: -0.0000

Data Index: 960109 (C4 (Web Text))

Max Activating Token Index: 760

Text #9

Max Range: 1.9421. Min Range: -1.9421

Max Act: 1.1766. Min Act: -0.0000

Data Index: 1030465 (C4 (Web Text))

Max Activating Token Index: 226

Text #10

Max Range: 1.9421. Min Range: -1.9421

Max Act: 1.2474. Min Act: -0.0000

Data Index: 356286 (C4 (Web Text))

Max Activating Token Index: 383

Text #11

Max Range: 1.9421. Min Range: -1.9421

Max Act: 1.2187. Min Act: -0.0000

Data Index: 72839 (C4 (Web Text))

Max Activating Token Index: 70

Text #12

Max Range: 1.9421. Min Range: -1.9421

Max Act: 1.1535. Min Act: -0.0000

Data Index: 382867 (C4 (Web Text))

Max Activating Token Index: 1000

Text #13

Max Range: 1.9421. Min Range: -1.9421

Max Act: 1.1897. Min Act: -0.0000

Data Index: 913596 (C4 (Web Text))

Max Activating Token Index: 77

Text #14

Max Range: 1.9421. Min Range: -1.9421

Max Act: 1.2460. Min Act: -0.0000

Data Index: 62419 (C4 (Web Text))

Max Activating Token Index: 700

Text #15

Max Range: 1.9421. Min Range: -1.9421

Max Act: 1.1061. Min Act: -0.0000

Data Index: 502853 (C4 (Web Text))

Max Activating Token Index: 112

Text #16

Max Range: 1.9421. Min Range: -1.9421

Max Act: 1.0802. Min Act: -0.0000

Data Index: 1228921 (C4 (Web Text))

Max Activating Token Index: 997

Text #17

Max Range: 1.9421. Min Range: -1.9421

Max Act: 1.0911. Min Act: -0.0000

Data Index: 274385 (C4 (Web Text))

Max Activating Token Index: 326

Text #18

Max Range: 1.9421. Min Range: -1.9421

Max Act: 1.0948. Min Act: -0.0000

Data Index: 1175119 (C4 (Web Text))

Max Activating Token Index: 704

Text #19

Max Range: 1.9421. Min Range: -1.9421

Max Act: 1.1499. Min Act: -0.0000

Data Index: 494457 (C4 (Web Text))

Max Activating Token Index: 292