Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 141 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6034. Min Range: -0.6034

Max Act: 0.6034. Min Act: -0.0000

Data Index: 1480350 (Python Code)

Max Activating Token Index: 498

Text #1

Max Range: 0.6034. Min Range: -0.6034

Max Act: 0.5351. Min Act: -0.0000

Data Index: 678925 (C4 (Web Text))

Max Activating Token Index: 134

Text #2

Max Range: 0.6034. Min Range: -0.6034

Max Act: 0.4964. Min Act: -0.0000

Data Index: 1519858 (Python Code)

Max Activating Token Index: 198

Text #3

Max Range: 0.6034. Min Range: -0.6034

Max Act: 0.4749. Min Act: -0.0001

Data Index: 1485856 (Python Code)

Max Activating Token Index: 481

Text #4

Max Range: 0.6034. Min Range: -0.6034

Max Act: 0.4449. Min Act: -0.0001

Data Index: 932988 (C4 (Web Text))

Max Activating Token Index: 84

Text #5

Max Range: 0.6034. Min Range: -0.6034

Max Act: 0.4748. Min Act: -0.0001

Data Index: 123091 (C4 (Web Text))

Max Activating Token Index: 55

Text #6

Max Range: 0.6034. Min Range: -0.6034

Max Act: 0.4636. Min Act: -0.0000

Data Index: 909807 (C4 (Web Text))

Max Activating Token Index: 718

Text #7

Max Range: 0.6034. Min Range: -0.6034

Max Act: 0.4415. Min Act: -0.0000

Data Index: 37687 (C4 (Web Text))

Max Activating Token Index: 1018

Text #8

Max Range: 0.6034. Min Range: -0.6034

Max Act: 0.4549. Min Act: -0.0000

Data Index: 475911 (C4 (Web Text))

Max Activating Token Index: 625

Text #9

Max Range: 0.6034. Min Range: -0.6034

Max Act: 0.4379. Min Act: -0.0000

Data Index: 96553 (C4 (Web Text))

Max Activating Token Index: 680

Text #10

Max Range: 0.6034. Min Range: -0.6034

Max Act: 0.4204. Min Act: -0.0001

Data Index: 864265 (C4 (Web Text))

Max Activating Token Index: 903

Text #11

Max Range: 0.6034. Min Range: -0.6034

Max Act: 0.3913. Min Act: -0.0000

Data Index: 15869 (C4 (Web Text))

Max Activating Token Index: 557

Text #12

Max Range: 0.6034. Min Range: -0.6034

Max Act: 0.4177. Min Act: -0.0000

Data Index: 1635568 (Python Code)

Max Activating Token Index: 904

Text #13

Max Range: 0.6034. Min Range: -0.6034

Max Act: 0.3840. Min Act: -0.0000

Data Index: 546620 (C4 (Web Text))

Max Activating Token Index: 456

Text #14

Max Range: 0.6034. Min Range: -0.6034

Max Act: 0.3679. Min Act: -0.0001

Data Index: 93754 (C4 (Web Text))

Max Activating Token Index: 692

Text #15

Max Range: 0.6034. Min Range: -0.6034

Max Act: 0.3977. Min Act: -0.0000

Data Index: 783336 (C4 (Web Text))

Max Activating Token Index: 198

Text #16

Max Range: 0.6034. Min Range: -0.6034

Max Act: 0.4187. Min Act: -0.0000

Data Index: 245921 (C4 (Web Text))

Max Activating Token Index: 709

Text #17

Max Range: 0.6034. Min Range: -0.6034

Max Act: 0.3459. Min Act: -0.0001

Data Index: 798707 (C4 (Web Text))

Max Activating Token Index: 364

Text #18

Max Range: 0.6034. Min Range: -0.6034

Max Act: 0.3941. Min Act: -0.0000

Data Index: 1224243 (C4 (Web Text))

Max Activating Token Index: 782

Text #19

Max Range: 0.6034. Min Range: -0.6034

Max Act: 0.3568. Min Act: -0.0000

Data Index: 1180137 (C4 (Web Text))

Max Activating Token Index: 196