Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 789 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.8953. Min Range: -1.8953

Max Act: 1.8589. Min Act: -0.0000

Data Index: 1559248 (The Pile)

Max Activating Token Index: 172

Text #1

Max Range: 1.8953. Min Range: -1.8953

Max Act: 1.8052. Min Act: -0.0000

Data Index: 1858199 (The Pile)

Max Activating Token Index: 225

Text #2

Max Range: 1.8953. Min Range: -1.8953

Max Act: 1.8953. Min Act: -0.0000

Data Index: 427502 (The Pile)

Max Activating Token Index: 154

Text #3

Max Range: 1.8953. Min Range: -1.8953

Max Act: 1.6775. Min Act: -0.0000

Data Index: 487869 (The Pile)

Max Activating Token Index: 92

Text #4

Max Range: 1.8953. Min Range: -1.8953

Max Act: 1.6770. Min Act: -0.0000

Data Index: 1422576 (The Pile)

Max Activating Token Index: 252

Text #5

Max Range: 1.8953. Min Range: -1.8953

Max Act: 1.4556. Min Act: -0.0000

Data Index: 190607 (The Pile)

Max Activating Token Index: 142

Text #6

Max Range: 1.8953. Min Range: -1.8953

Max Act: 1.3025. Min Act: -0.0000

Data Index: 15360 (The Pile)

Max Activating Token Index: 36

Text #7

Max Range: 1.8953. Min Range: -1.8953

Max Act: 1.2605. Min Act: -0.0000

Data Index: 1145570 (The Pile)

Max Activating Token Index: 828

Text #8

Max Range: 1.8953. Min Range: -1.8953

Max Act: 1.2438. Min Act: -0.0000

Data Index: 1177472 (The Pile)

Max Activating Token Index: 578

Text #9

Max Range: 1.8953. Min Range: -1.8953

Max Act: 1.1929. Min Act: -0.0000

Data Index: 1330028 (The Pile)

Max Activating Token Index: 367

Text #10

Max Range: 1.8953. Min Range: -1.8953

Max Act: 1.1366. Min Act: -0.0000

Data Index: 1265945 (The Pile)

Max Activating Token Index: 1013

Text #11

Max Range: 1.8953. Min Range: -1.8953

Max Act: 1.1841. Min Act: -0.0000

Data Index: 464719 (The Pile)

Max Activating Token Index: 347

Text #12

Max Range: 1.8953. Min Range: -1.8953

Max Act: 1.2037. Min Act: -0.0000

Data Index: 1143285 (The Pile)

Max Activating Token Index: 908

Text #13

Max Range: 1.8953. Min Range: -1.8953

Max Act: 1.2414. Min Act: -0.0000

Data Index: 891910 (The Pile)

Max Activating Token Index: 324

Text #14

Max Range: 1.8953. Min Range: -1.8953

Max Act: 1.3007. Min Act: -0.0000

Data Index: 259812 (The Pile)

Max Activating Token Index: 1006

Text #15

Max Range: 1.8953. Min Range: -1.8953

Max Act: 1.0958. Min Act: -0.0000

Data Index: 5247 (The Pile)

Max Activating Token Index: 177

Text #16

Max Range: 1.8953. Min Range: -1.8953

Max Act: 1.1536. Min Act: -0.0000

Data Index: 1506323 (The Pile)

Max Activating Token Index: 643

Text #17

Max Range: 1.8953. Min Range: -1.8953

Max Act: 1.0444. Min Act: -0.0000

Data Index: 390285 (The Pile)

Max Activating Token Index: 300

Text #18

Max Range: 1.8953. Min Range: -1.8953

Max Act: 1.0871. Min Act: -0.0000

Data Index: 706873 (The Pile)

Max Activating Token Index: 23

Text #19

Max Range: 1.8953. Min Range: -1.8953

Max Act: 1.0179. Min Act: -0.0000

Data Index: 670296 (The Pile)

Max Activating Token Index: 57