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

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

Neuron 811 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.5514. Min Act: -0.0000

Data Index: 905513 (C4 (Web Text))

Max Activating Token Index: 43

Text #1

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.5109. Min Act: -0.0000

Data Index: 8547 (C4 (Web Text))

Max Activating Token Index: 869

Text #2

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.5245. Min Act: -0.0000

Data Index: 586802 (C4 (Web Text))

Max Activating Token Index: 774

Text #3

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.4996. Min Act: -0.0000

Data Index: 318619 (C4 (Web Text))

Max Activating Token Index: 56

Text #4

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.5131. Min Act: -0.0000

Data Index: 1253821 (C4 (Web Text))

Max Activating Token Index: 810

Text #5

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.4665. Min Act: -0.0000

Data Index: 981847 (C4 (Web Text))

Max Activating Token Index: 922

Text #6

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.4758. Min Act: -0.0000

Data Index: 127633 (C4 (Web Text))

Max Activating Token Index: 463

Text #7

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.5367. Min Act: -0.0000

Data Index: 250744 (C4 (Web Text))

Max Activating Token Index: 941

Text #8

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.4534. Min Act: -0.0000

Data Index: 685504 (C4 (Web Text))

Max Activating Token Index: 988

Text #9

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.4070. Min Act: -0.0000

Data Index: 522148 (C4 (Web Text))

Max Activating Token Index: 437

Text #10

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.4251. Min Act: -0.0000

Data Index: 1048894 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.4306. Min Act: -0.0000

Data Index: 557001 (C4 (Web Text))

Max Activating Token Index: 111

Text #12

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.4225. Min Act: -0.0000

Data Index: 92180 (C4 (Web Text))

Max Activating Token Index: 991

Text #13

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.4369. Min Act: -0.0000

Data Index: 176643 (C4 (Web Text))

Max Activating Token Index: 18

Text #14

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.4292. Min Act: -0.0000

Data Index: 1125660 (C4 (Web Text))

Max Activating Token Index: 676

Text #15

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.4181. Min Act: -0.0000

Data Index: 1004711 (C4 (Web Text))

Max Activating Token Index: 43

Text #16

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.4000. Min Act: -0.0000

Data Index: 48926 (C4 (Web Text))

Max Activating Token Index: 383

Text #17

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.4029. Min Act: -0.0000

Data Index: 293308 (C4 (Web Text))

Max Activating Token Index: 629

Text #18

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.4154. Min Act: -0.0000

Data Index: 513117 (C4 (Web Text))

Max Activating Token Index: 845

Text #19

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.3898. Min Act: -0.0000

Data Index: 901242 (C4 (Web Text))

Max Activating Token Index: 269