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

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

Neuron 82 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: 5.0075. Min Range: -5.0075

Max Act: 5.0075. Min Act: -0.0000

Data Index: 271530 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 5.0075. Min Range: -5.0075

Max Act: 4.6226. Min Act: -0.0000

Data Index: 781548 (C4 (Web Text))

Max Activating Token Index: 56

Text #2

Max Range: 5.0075. Min Range: -5.0075

Max Act: 4.6386. Min Act: -0.0000

Data Index: 49712 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 5.0075. Min Range: -5.0075

Max Act: 4.6542. Min Act: -0.0000

Data Index: 1034705 (C4 (Web Text))

Max Activating Token Index: 25

Text #4

Max Range: 5.0075. Min Range: -5.0075

Max Act: 4.5817. Min Act: -0.0000

Data Index: 268217 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 5.0075. Min Range: -5.0075

Max Act: 4.2686. Min Act: -0.0000

Data Index: 556445 (C4 (Web Text))

Max Activating Token Index: 105

Text #6

Max Range: 5.0075. Min Range: -5.0075

Max Act: 4.4363. Min Act: -0.0000

Data Index: 646609 (C4 (Web Text))

Max Activating Token Index: 180

Text #7

Max Range: 5.0075. Min Range: -5.0075

Max Act: 4.4110. Min Act: -0.0000

Data Index: 348844 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 5.0075. Min Range: -5.0075

Max Act: 4.3787. Min Act: -0.0000

Data Index: 1276764 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 5.0075. Min Range: -5.0075

Max Act: 4.1851. Min Act: -0.0000

Data Index: 1042910 (C4 (Web Text))

Max Activating Token Index: 25

Text #10

Max Range: 5.0075. Min Range: -5.0075

Max Act: 4.3108. Min Act: -0.0000

Data Index: 1294367 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 5.0075. Min Range: -5.0075

Max Act: 4.2169. Min Act: -0.0000

Data Index: 204677 (C4 (Web Text))

Max Activating Token Index: 57

Text #12

Max Range: 5.0075. Min Range: -5.0075

Max Act: 4.2356. Min Act: -0.0000

Data Index: 936476 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 5.0075. Min Range: -5.0075

Max Act: 4.3073. Min Act: -0.0000

Data Index: 1273274 (C4 (Web Text))

Max Activating Token Index: 311

Text #14

Max Range: 5.0075. Min Range: -5.0075

Max Act: 4.1149. Min Act: -0.0000

Data Index: 1012580 (C4 (Web Text))

Max Activating Token Index: 48

Text #15

Max Range: 5.0075. Min Range: -5.0075

Max Act: 4.0639. Min Act: -0.0000

Data Index: 828993 (C4 (Web Text))

Max Activating Token Index: 84

Text #16

Max Range: 5.0075. Min Range: -5.0075

Max Act: 3.7541. Min Act: -0.0000

Data Index: 798732 (C4 (Web Text))

Max Activating Token Index: 906

Text #17

Max Range: 5.0075. Min Range: -5.0075

Max Act: 4.0264. Min Act: -0.0000

Data Index: 1190681 (C4 (Web Text))

Max Activating Token Index: 159

Text #18

Max Range: 5.0075. Min Range: -5.0075

Max Act: 4.0311. Min Act: -0.0000

Data Index: 877319 (C4 (Web Text))

Max Activating Token Index: 550

Text #19

Max Range: 5.0075. Min Range: -5.0075

Max Act: 4.0361. Min Act: -0.0000

Data Index: 638771 (C4 (Web Text))

Max Activating Token Index: 185