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

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

Neuron 2102 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: 0.5295. Min Range: -0.5295

Max Act: 0.5295. Min Act: -0.0001

Data Index: 1420484 (Python Code)

Max Activating Token Index: 1017

Text #1

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.4719. Min Act: -0.0000

Data Index: 981223 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.4572. Min Act: -0.0000

Data Index: 15048 (C4 (Web Text))

Max Activating Token Index: 240

Text #3

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.3087. Min Act: -0.0001

Data Index: 389136 (C4 (Web Text))

Max Activating Token Index: 795

Text #4

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.2948. Min Act: -0.0000

Data Index: 23251 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.3056. Min Act: -0.0000

Data Index: 349965 (C4 (Web Text))

Max Activating Token Index: 742

Text #6

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.3347. Min Act: -0.0000

Data Index: 1016223 (C4 (Web Text))

Max Activating Token Index: 556

Text #7

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.3272. Min Act: -0.0000

Data Index: 1007131 (C4 (Web Text))

Max Activating Token Index: 572

Text #8

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.2929. Min Act: -0.0000

Data Index: 946183 (C4 (Web Text))

Max Activating Token Index: 327

Text #9

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.3004. Min Act: -0.0000

Data Index: 599516 (C4 (Web Text))

Max Activating Token Index: 385

Text #10

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.2935. Min Act: -0.0000

Data Index: 1237579 (C4 (Web Text))

Max Activating Token Index: 607

Text #11

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.3109. Min Act: -0.0000

Data Index: 164199 (C4 (Web Text))

Max Activating Token Index: 502

Text #12

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.3010. Min Act: -0.0001

Data Index: 430213 (C4 (Web Text))

Max Activating Token Index: 300

Text #13

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.2886. Min Act: 0.0000

Data Index: 1619244 (Python Code)

Max Activating Token Index: 430

Text #14

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.2868. Min Act: -0.0000

Data Index: 801535 (C4 (Web Text))

Max Activating Token Index: 218

Text #15

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.2714. Min Act: -0.0000

Data Index: 768302 (C4 (Web Text))

Max Activating Token Index: 1017

Text #16

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.2788. Min Act: 0.0000

Data Index: 969983 (C4 (Web Text))

Max Activating Token Index: 511

Text #17

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.2722. Min Act: -0.0000

Data Index: 1042601 (C4 (Web Text))

Max Activating Token Index: 925

Text #18

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.2798. Min Act: -0.0000

Data Index: 213935 (C4 (Web Text))

Max Activating Token Index: 974

Text #19

Max Range: 0.5295. Min Range: -0.5295

Max Act: 0.2860. Min Act: -0.0000

Data Index: 1283924 (C4 (Web Text))

Max Activating Token Index: 543