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

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

Neuron 3966 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2147. Min Range: -3.2147

Max Act: 3.2147. Min Act: -0.0000

Data Index: 831317 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 3.2147. Min Range: -3.2147

Max Act: 2.3074. Min Act: -0.0000

Data Index: 1090956 (C4 (Web Text))

Max Activating Token Index: 804

Text #2

Max Range: 3.2147. Min Range: -3.2147

Max Act: 2.2034. Min Act: -0.0000

Data Index: 1309708 (C4 (Web Text))

Max Activating Token Index: 255

Text #3

Max Range: 3.2147. Min Range: -3.2147

Max Act: 2.1183. Min Act: -0.0000

Data Index: 240396 (C4 (Web Text))

Max Activating Token Index: 672

Text #4

Max Range: 3.2147. Min Range: -3.2147

Max Act: 2.0678. Min Act: -0.0000

Data Index: 144674 (C4 (Web Text))

Max Activating Token Index: 185

Text #5

Max Range: 3.2147. Min Range: -3.2147

Max Act: 1.8721. Min Act: -0.0000

Data Index: 1303383 (C4 (Web Text))

Max Activating Token Index: 475

Text #6

Max Range: 3.2147. Min Range: -3.2147

Max Act: 1.6795. Min Act: -0.0000

Data Index: 123199 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 3.2147. Min Range: -3.2147

Max Act: 1.6795. Min Act: -0.0000

Data Index: 1009106 (C4 (Web Text))

Max Activating Token Index: 819

Text #8

Max Range: 3.2147. Min Range: -3.2147

Max Act: 1.6357. Min Act: -0.0000

Data Index: 340423 (C4 (Web Text))

Max Activating Token Index: 133

Text #9

Max Range: 3.2147. Min Range: -3.2147

Max Act: 1.6172. Min Act: -0.0000

Data Index: 1298508 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 3.2147. Min Range: -3.2147

Max Act: 1.7060. Min Act: -0.0000

Data Index: 1225790 (C4 (Web Text))

Max Activating Token Index: 323

Text #11

Max Range: 3.2147. Min Range: -3.2147

Max Act: 1.5281. Min Act: -0.0000

Data Index: 490426 (C4 (Web Text))

Max Activating Token Index: 760

Text #12

Max Range: 3.2147. Min Range: -3.2147

Max Act: 1.4729. Min Act: -0.0000

Data Index: 1198842 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 3.2147. Min Range: -3.2147

Max Act: 1.4370. Min Act: -0.0000

Data Index: 133315 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 3.2147. Min Range: -3.2147

Max Act: 1.4690. Min Act: -0.0000

Data Index: 1033794 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 3.2147. Min Range: -3.2147

Max Act: 1.5506. Min Act: -0.0000

Data Index: 788453 (C4 (Web Text))

Max Activating Token Index: 703

Text #16

Max Range: 3.2147. Min Range: -3.2147

Max Act: 1.4622. Min Act: -0.0000

Data Index: 375259 (C4 (Web Text))

Max Activating Token Index: 951

Text #17

Max Range: 3.2147. Min Range: -3.2147

Max Act: 1.4600. Min Act: -0.0000

Data Index: 633222 (C4 (Web Text))

Max Activating Token Index: 962

Text #18

Max Range: 3.2147. Min Range: -3.2147

Max Act: 1.4488. Min Act: -0.0000

Data Index: 364084 (C4 (Web Text))

Max Activating Token Index: 789

Text #19

Max Range: 3.2147. Min Range: -3.2147

Max Act: 1.3569. Min Act: -0.0000

Data Index: 267757 (C4 (Web Text))

Max Activating Token Index: 429