Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4160 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.4954. Min Act: -0.0002

Data Index: 738862 (C4 (Web Text))

Max Activating Token Index: 332

Text #1

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.4508. Min Act: -0.0002

Data Index: 835651 (C4 (Web Text))

Max Activating Token Index: 109

Text #2

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.4383. Min Act: -0.0002

Data Index: 342065 (C4 (Web Text))

Max Activating Token Index: 342

Text #3

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.4312. Min Act: -0.0002

Data Index: 560269 (C4 (Web Text))

Max Activating Token Index: 549

Text #4

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.4136. Min Act: -0.0002

Data Index: 99289 (C4 (Web Text))

Max Activating Token Index: 489

Text #5

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.4136. Min Act: -0.0002

Data Index: 1296389 (C4 (Web Text))

Max Activating Token Index: 246

Text #6

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.3950. Min Act: -0.0002

Data Index: 711259 (C4 (Web Text))

Max Activating Token Index: 672

Text #7

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.4034. Min Act: -0.0002

Data Index: 463347 (C4 (Web Text))

Max Activating Token Index: 600

Text #8

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.4046. Min Act: -0.0002

Data Index: 906074 (C4 (Web Text))

Max Activating Token Index: 111

Text #9

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.4039. Min Act: -0.0002

Data Index: 1439 (C4 (Web Text))

Max Activating Token Index: 59

Text #10

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.3891. Min Act: -0.0002

Data Index: 466787 (C4 (Web Text))

Max Activating Token Index: 817

Text #11

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.3856. Min Act: -0.0002

Data Index: 1154879 (C4 (Web Text))

Max Activating Token Index: 592

Text #12

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.3824. Min Act: -0.0002

Data Index: 111594 (C4 (Web Text))

Max Activating Token Index: 398

Text #13

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.3909. Min Act: -0.0002

Data Index: 1087054 (C4 (Web Text))

Max Activating Token Index: 559

Text #14

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.3628. Min Act: -0.0002

Data Index: 1232290 (C4 (Web Text))

Max Activating Token Index: 251

Text #15

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.3913. Min Act: -0.0002

Data Index: 141604 (C4 (Web Text))

Max Activating Token Index: 72

Text #16

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.3921. Min Act: -0.0002

Data Index: 1026060 (C4 (Web Text))

Max Activating Token Index: 238

Text #17

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.3739. Min Act: -0.0002

Data Index: 121557 (C4 (Web Text))

Max Activating Token Index: 672

Text #18

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.3866. Min Act: -0.0002

Data Index: 1359070 (C4 (Web Text))

Max Activating Token Index: 138

Text #19

Max Range: 0.4954. Min Range: -0.4954

Max Act: 0.3694. Min Act: -0.0002

Data Index: 734500 (C4 (Web Text))

Max Activating Token Index: 321