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

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

Neuron 124 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7893. Min Range: -4.7893

Max Act: 4.7655. Min Act: -0.0001

Data Index: 960914 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 4.7893. Min Range: -4.7893

Max Act: 4.7893. Min Act: -0.0001

Data Index: 1080287 (C4 (Web Text))

Max Activating Token Index: 866

Text #2

Max Range: 4.7893. Min Range: -4.7893

Max Act: 3.8472. Min Act: -0.0001

Data Index: 1196507 (C4 (Web Text))

Max Activating Token Index: 835

Text #3

Max Range: 4.7893. Min Range: -4.7893

Max Act: 4.2015. Min Act: -0.0001

Data Index: 1291669 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 4.7893. Min Range: -4.7893

Max Act: 3.4574. Min Act: -0.0000

Data Index: 346788 (C4 (Web Text))

Max Activating Token Index: 214

Text #5

Max Range: 4.7893. Min Range: -4.7893

Max Act: 3.8573. Min Act: -0.0001

Data Index: 124719 (C4 (Web Text))

Max Activating Token Index: 993

Text #6

Max Range: 4.7893. Min Range: -4.7893

Max Act: 3.9840. Min Act: -0.0001

Data Index: 866226 (C4 (Web Text))

Max Activating Token Index: 424

Text #7

Max Range: 4.7893. Min Range: -4.7893

Max Act: 3.6152. Min Act: -0.0001

Data Index: 1223471 (C4 (Web Text))

Max Activating Token Index: 240

Text #8

Max Range: 4.7893. Min Range: -4.7893

Max Act: 3.7904. Min Act: -0.0000

Data Index: 202051 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 4.7893. Min Range: -4.7893

Max Act: 3.7469. Min Act: -0.0000

Data Index: 801184 (C4 (Web Text))

Max Activating Token Index: 506

Text #10

Max Range: 4.7893. Min Range: -4.7893

Max Act: 3.7349. Min Act: -0.0001

Data Index: 1138714 (C4 (Web Text))

Max Activating Token Index: 598

Text #11

Max Range: 4.7893. Min Range: -4.7893

Max Act: 3.5566. Min Act: -0.0000

Data Index: 1134033 (C4 (Web Text))

Max Activating Token Index: 20

Text #12

Max Range: 4.7893. Min Range: -4.7893

Max Act: 3.5448. Min Act: -0.0000

Data Index: 94555 (C4 (Web Text))

Max Activating Token Index: 380

Text #13

Max Range: 4.7893. Min Range: -4.7893

Max Act: 3.6564. Min Act: -0.0001

Data Index: 21189 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 4.7893. Min Range: -4.7893

Max Act: 3.7884. Min Act: -0.0000

Data Index: 328455 (C4 (Web Text))

Max Activating Token Index: 596

Text #15

Max Range: 4.7893. Min Range: -4.7893

Max Act: 3.4388. Min Act: -0.0000

Data Index: 1347530 (C4 (Web Text))

Max Activating Token Index: 1005

Text #16

Max Range: 4.7893. Min Range: -4.7893

Max Act: 3.1301. Min Act: -0.0000

Data Index: 286590 (C4 (Web Text))

Max Activating Token Index: 954

Text #17

Max Range: 4.7893. Min Range: -4.7893

Max Act: 3.3777. Min Act: -0.0000

Data Index: 820988 (C4 (Web Text))

Max Activating Token Index: 536

Text #18

Max Range: 4.7893. Min Range: -4.7893

Max Act: 3.5208. Min Act: -0.0000

Data Index: 422846 (C4 (Web Text))

Max Activating Token Index: 776

Text #19

Max Range: 4.7893. Min Range: -4.7893

Max Act: 3.5056. Min Act: -0.0001

Data Index: 91989 (C4 (Web Text))

Max Activating Token Index: 144