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

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

Neuron 4975 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3528. Min Range: -0.3528

Max Act: 0.3528. Min Act: -0.0000

Data Index: 906049 (C4 (Web Text))

Max Activating Token Index: 815

Text #1

Max Range: 0.3528. Min Range: -0.3528

Max Act: 0.3385. Min Act: -0.0000

Data Index: 481202 (C4 (Web Text))

Max Activating Token Index: 785

Text #2

Max Range: 0.3528. Min Range: -0.3528

Max Act: 0.3179. Min Act: -0.0000

Data Index: 150338 (C4 (Web Text))

Max Activating Token Index: 5

Text #3

Max Range: 0.3528. Min Range: -0.3528

Max Act: 0.2826. Min Act: -0.0000

Data Index: 113341 (C4 (Web Text))

Max Activating Token Index: 386

Text #4

Max Range: 0.3528. Min Range: -0.3528

Max Act: 0.2976. Min Act: -0.0000

Data Index: 965819 (C4 (Web Text))

Max Activating Token Index: 335

Text #5

Max Range: 0.3528. Min Range: -0.3528

Max Act: 0.2768. Min Act: -0.0000

Data Index: 728675 (C4 (Web Text))

Max Activating Token Index: 192

Text #6

Max Range: 0.3528. Min Range: -0.3528

Max Act: 0.2766. Min Act: -0.0000

Data Index: 846921 (C4 (Web Text))

Max Activating Token Index: 79

Text #7

Max Range: 0.3528. Min Range: -0.3528

Max Act: 0.2736. Min Act: -0.0001

Data Index: 73697 (C4 (Web Text))

Max Activating Token Index: 899

Text #8

Max Range: 0.3528. Min Range: -0.3528

Max Act: 0.2278. Min Act: -0.0000

Data Index: 557224 (C4 (Web Text))

Max Activating Token Index: 228

Text #9

Max Range: 0.3528. Min Range: -0.3528

Max Act: 0.2634. Min Act: -0.0001

Data Index: 637761 (C4 (Web Text))

Max Activating Token Index: 528

Text #10

Max Range: 0.3528. Min Range: -0.3528

Max Act: 0.2495. Min Act: -0.0000

Data Index: 1084665 (C4 (Web Text))

Max Activating Token Index: 74

Text #11

Max Range: 0.3528. Min Range: -0.3528

Max Act: 0.2462. Min Act: -0.0000

Data Index: 1359244 (C4 (Web Text))

Max Activating Token Index: 451

Text #12

Max Range: 0.3528. Min Range: -0.3528

Max Act: 0.2641. Min Act: -0.0000

Data Index: 330464 (C4 (Web Text))

Max Activating Token Index: 713

Text #13

Max Range: 0.3528. Min Range: -0.3528

Max Act: 0.2366. Min Act: -0.0000

Data Index: 245558 (C4 (Web Text))

Max Activating Token Index: 19

Text #14

Max Range: 0.3528. Min Range: -0.3528

Max Act: 0.2311. Min Act: -0.0000

Data Index: 648120 (C4 (Web Text))

Max Activating Token Index: 923

Text #15

Max Range: 0.3528. Min Range: -0.3528

Max Act: 0.2333. Min Act: -0.0000

Data Index: 403994 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 0.3528. Min Range: -0.3528

Max Act: 0.2362. Min Act: -0.0000

Data Index: 585475 (C4 (Web Text))

Max Activating Token Index: 364

Text #17

Max Range: 0.3528. Min Range: -0.3528

Max Act: 0.2306. Min Act: -0.0000

Data Index: 371528 (C4 (Web Text))

Max Activating Token Index: 255

Text #18

Max Range: 0.3528. Min Range: -0.3528

Max Act: 0.2425. Min Act: -0.0000

Data Index: 1353591 (C4 (Web Text))

Max Activating Token Index: 208

Text #19

Max Range: 0.3528. Min Range: -0.3528

Max Act: 0.2396. Min Act: -0.0000

Data Index: 923157 (C4 (Web Text))

Max Activating Token Index: 403