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

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

Neuron 1234 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2745. Min Range: -3.2745

Max Act: 3.2745. Min Act: -0.0000

Data Index: 364926 (C4 (Web Text))

Max Activating Token Index: 107

Text #1

Max Range: 3.2745. Min Range: -3.2745

Max Act: 2.7533. Min Act: 0.0000

Data Index: 811254 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 3.2745. Min Range: -3.2745

Max Act: 2.5561. Min Act: -0.0000

Data Index: 316113 (C4 (Web Text))

Max Activating Token Index: 576

Text #3

Max Range: 3.2745. Min Range: -3.2745

Max Act: 2.5147. Min Act: -0.0000

Data Index: 233339 (C4 (Web Text))

Max Activating Token Index: 577

Text #4

Max Range: 3.2745. Min Range: -3.2745

Max Act: 2.5756. Min Act: -0.0000

Data Index: 1061654 (C4 (Web Text))

Max Activating Token Index: 823

Text #5

Max Range: 3.2745. Min Range: -3.2745

Max Act: 2.0369. Min Act: -0.0000

Data Index: 242096 (C4 (Web Text))

Max Activating Token Index: 227

Text #6

Max Range: 3.2745. Min Range: -3.2745

Max Act: 2.3842. Min Act: -0.0000

Data Index: 227229 (C4 (Web Text))

Max Activating Token Index: 933

Text #7

Max Range: 3.2745. Min Range: -3.2745

Max Act: 2.3510. Min Act: -0.0000

Data Index: 634797 (C4 (Web Text))

Max Activating Token Index: 499

Text #8

Max Range: 3.2745. Min Range: -3.2745

Max Act: 2.0846. Min Act: -0.0000

Data Index: 504566 (C4 (Web Text))

Max Activating Token Index: 258

Text #9

Max Range: 3.2745. Min Range: -3.2745

Max Act: 2.2826. Min Act: -0.0000

Data Index: 1255534 (C4 (Web Text))

Max Activating Token Index: 745

Text #10

Max Range: 3.2745. Min Range: -3.2745

Max Act: 2.0935. Min Act: -0.0000

Data Index: 578375 (C4 (Web Text))

Max Activating Token Index: 490

Text #11

Max Range: 3.2745. Min Range: -3.2745

Max Act: 2.0228. Min Act: -0.0000

Data Index: 1151612 (C4 (Web Text))

Max Activating Token Index: 129

Text #12

Max Range: 3.2745. Min Range: -3.2745

Max Act: 1.9011. Min Act: 0.0000

Data Index: 588887 (C4 (Web Text))

Max Activating Token Index: 159

Text #13

Max Range: 3.2745. Min Range: -3.2745

Max Act: 2.1233. Min Act: -0.0000

Data Index: 380086 (C4 (Web Text))

Max Activating Token Index: 843

Text #14

Max Range: 3.2745. Min Range: -3.2745

Max Act: 1.9015. Min Act: -0.0000

Data Index: 1169659 (C4 (Web Text))

Max Activating Token Index: 1002

Text #15

Max Range: 3.2745. Min Range: -3.2745

Max Act: 2.1008. Min Act: -0.0000

Data Index: 11606 (C4 (Web Text))

Max Activating Token Index: 721

Text #16

Max Range: 3.2745. Min Range: -3.2745

Max Act: 1.8699. Min Act: -0.0000

Data Index: 616130 (C4 (Web Text))

Max Activating Token Index: 338

Text #17

Max Range: 3.2745. Min Range: -3.2745

Max Act: 1.8513. Min Act: -0.0000

Data Index: 1085314 (C4 (Web Text))

Max Activating Token Index: 895

Text #18

Max Range: 3.2745. Min Range: -3.2745

Max Act: 1.7345. Min Act: -0.0000

Data Index: 878746 (C4 (Web Text))

Max Activating Token Index: 292

Text #19

Max Range: 3.2745. Min Range: -3.2745

Max Act: 1.8121. Min Act: -0.0000

Data Index: 54020 (C4 (Web Text))

Max Activating Token Index: 522