Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 455 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1251. Min Range: -1.1251

Max Act: 1.1238. Min Act: -0.0001

Data Index: 628314 (C4 (Web Text))

Max Activating Token Index: 471

Text #1

Max Range: 1.1251. Min Range: -1.1251

Max Act: 1.0380. Min Act: -0.0002

Data Index: 988647 (C4 (Web Text))

Max Activating Token Index: 554

Text #2

Max Range: 1.1251. Min Range: -1.1251

Max Act: 1.0623. Min Act: -0.0002

Data Index: 1291053 (C4 (Web Text))

Max Activating Token Index: 331

Text #3

Max Range: 1.1251. Min Range: -1.1251

Max Act: 1.0873. Min Act: -0.0002

Data Index: 1079147 (C4 (Web Text))

Max Activating Token Index: 422

Text #4

Max Range: 1.1251. Min Range: -1.1251

Max Act: 1.0495. Min Act: -0.0001

Data Index: 279680 (C4 (Web Text))

Max Activating Token Index: 177

Text #5

Max Range: 1.1251. Min Range: -1.1251

Max Act: 1.0100. Min Act: -0.0002

Data Index: 881626 (C4 (Web Text))

Max Activating Token Index: 911

Text #6

Max Range: 1.1251. Min Range: -1.1251

Max Act: 1.0077. Min Act: -0.0002

Data Index: 266730 (C4 (Web Text))

Max Activating Token Index: 686

Text #7

Max Range: 1.1251. Min Range: -1.1251

Max Act: 1.1251. Min Act: -0.0002

Data Index: 943988 (C4 (Web Text))

Max Activating Token Index: 950

Text #8

Max Range: 1.1251. Min Range: -1.1251

Max Act: 1.0188. Min Act: -0.0002

Data Index: 511765 (C4 (Web Text))

Max Activating Token Index: 463

Text #9

Max Range: 1.1251. Min Range: -1.1251

Max Act: 1.0011. Min Act: -0.0002

Data Index: 749727 (C4 (Web Text))

Max Activating Token Index: 422

Text #10

Max Range: 1.1251. Min Range: -1.1251

Max Act: 0.9603. Min Act: -0.0001

Data Index: 989766 (C4 (Web Text))

Max Activating Token Index: 99

Text #11

Max Range: 1.1251. Min Range: -1.1251

Max Act: 0.9612. Min Act: -0.0002

Data Index: 599312 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 1.1251. Min Range: -1.1251

Max Act: 0.9852. Min Act: -0.0002

Data Index: 837525 (C4 (Web Text))

Max Activating Token Index: 250

Text #13

Max Range: 1.1251. Min Range: -1.1251

Max Act: 1.0157. Min Act: -0.0002

Data Index: 460588 (C4 (Web Text))

Max Activating Token Index: 159

Text #14

Max Range: 1.1251. Min Range: -1.1251

Max Act: 0.9810. Min Act: -0.0002

Data Index: 851898 (C4 (Web Text))

Max Activating Token Index: 199

Text #15

Max Range: 1.1251. Min Range: -1.1251

Max Act: 1.0435. Min Act: -0.0002

Data Index: 981467 (C4 (Web Text))

Max Activating Token Index: 312

Text #16

Max Range: 1.1251. Min Range: -1.1251

Max Act: 0.9494. Min Act: -0.0002

Data Index: 431886 (C4 (Web Text))

Max Activating Token Index: 608

Text #17

Max Range: 1.1251. Min Range: -1.1251

Max Act: 0.9651. Min Act: -0.0001

Data Index: 998366 (C4 (Web Text))

Max Activating Token Index: 944

Text #18

Max Range: 1.1251. Min Range: -1.1251

Max Act: 0.9591. Min Act: -0.0001

Data Index: 28420 (C4 (Web Text))

Max Activating Token Index: 8

Text #19

Max Range: 1.1251. Min Range: -1.1251

Max Act: 0.9920. Min Act: -0.0001

Data Index: 469564 (C4 (Web Text))

Max Activating Token Index: 701