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

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

Neuron 1792 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: 2.3256. Min Range: -2.3256

Max Act: 2.3256. Min Act: -0.0001

Data Index: 1100526 (C4 (Web Text))

Max Activating Token Index: 41

Text #1

Max Range: 2.3256. Min Range: -2.3256

Max Act: 2.0582. Min Act: -0.0000

Data Index: 340173 (C4 (Web Text))

Max Activating Token Index: 913

Text #2

Max Range: 2.3256. Min Range: -2.3256

Max Act: 1.7406. Min Act: -0.0000

Data Index: 165032 (C4 (Web Text))

Max Activating Token Index: 581

Text #3

Max Range: 2.3256. Min Range: -2.3256

Max Act: 1.5403. Min Act: -0.0000

Data Index: 460781 (C4 (Web Text))

Max Activating Token Index: 693

Text #4

Max Range: 2.3256. Min Range: -2.3256

Max Act: 1.7096. Min Act: -0.0000

Data Index: 839225 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 2.3256. Min Range: -2.3256

Max Act: 1.5980. Min Act: -0.0001

Data Index: 382821 (C4 (Web Text))

Max Activating Token Index: 778

Text #6

Max Range: 2.3256. Min Range: -2.3256

Max Act: 1.4343. Min Act: -0.0000

Data Index: 1119138 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 2.3256. Min Range: -2.3256

Max Act: 1.3851. Min Act: -0.0000

Data Index: 1122509 (C4 (Web Text))

Max Activating Token Index: 519

Text #8

Max Range: 2.3256. Min Range: -2.3256

Max Act: 1.3927. Min Act: -0.0001

Data Index: 912117 (C4 (Web Text))

Max Activating Token Index: 996

Text #9

Max Range: 2.3256. Min Range: -2.3256

Max Act: 1.3674. Min Act: -0.0001

Data Index: 198024 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 2.3256. Min Range: -2.3256

Max Act: 1.3452. Min Act: -0.0000

Data Index: 846212 (C4 (Web Text))

Max Activating Token Index: 1007

Text #11

Max Range: 2.3256. Min Range: -2.3256

Max Act: 1.2863. Min Act: -0.0000

Data Index: 460564 (C4 (Web Text))

Max Activating Token Index: 826

Text #12

Max Range: 2.3256. Min Range: -2.3256

Max Act: 1.3596. Min Act: -0.0001

Data Index: 793504 (C4 (Web Text))

Max Activating Token Index: 678

Text #13

Max Range: 2.3256. Min Range: -2.3256

Max Act: 1.2766. Min Act: -0.0001

Data Index: 456138 (C4 (Web Text))

Max Activating Token Index: 872

Text #14

Max Range: 2.3256. Min Range: -2.3256

Max Act: 1.3554. Min Act: -0.0001

Data Index: 965922 (C4 (Web Text))

Max Activating Token Index: 63

Text #15

Max Range: 2.3256. Min Range: -2.3256

Max Act: 1.3254. Min Act: -0.0001

Data Index: 1148089 (C4 (Web Text))

Max Activating Token Index: 169

Text #16

Max Range: 2.3256. Min Range: -2.3256

Max Act: 1.2941. Min Act: -0.0001

Data Index: 132557 (C4 (Web Text))

Max Activating Token Index: 395

Text #17

Max Range: 2.3256. Min Range: -2.3256

Max Act: 1.2377. Min Act: -0.0000

Data Index: 1287641 (C4 (Web Text))

Max Activating Token Index: 146

Text #18

Max Range: 2.3256. Min Range: -2.3256

Max Act: 1.3073. Min Act: -0.0001

Data Index: 1172542 (C4 (Web Text))

Max Activating Token Index: 477

Text #19

Max Range: 2.3256. Min Range: -2.3256

Max Act: 1.3596. Min Act: -0.0000

Data Index: 64315 (C4 (Web Text))

Max Activating Token Index: 490