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

Dataset: The Pile

Neuron 3486 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.5150. Min Act: -0.0000

Data Index: 308218 (The Pile)

Max Activating Token Index: 51

Text #1

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.4322. Min Act: -0.0000

Data Index: 1781889 (The Pile)

Max Activating Token Index: 167

Text #2

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.4346. Min Act: -0.0000

Data Index: 345848 (The Pile)

Max Activating Token Index: 707

Text #3

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.3859. Min Act: -0.0000

Data Index: 1562068 (The Pile)

Max Activating Token Index: 560

Text #4

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.3837. Min Act: -0.0000

Data Index: 1622500 (The Pile)

Max Activating Token Index: 112

Text #5

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.3717. Min Act: -0.0000

Data Index: 548893 (The Pile)

Max Activating Token Index: 16

Text #6

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.3713. Min Act: -0.0000

Data Index: 603045 (The Pile)

Max Activating Token Index: 734

Text #7

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.3584. Min Act: -0.0000

Data Index: 1948283 (The Pile)

Max Activating Token Index: 698

Text #8

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.3239. Min Act: -0.0000

Data Index: 1634274 (The Pile)

Max Activating Token Index: 801

Text #9

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.3116. Min Act: -0.0000

Data Index: 194193 (The Pile)

Max Activating Token Index: 260

Text #10

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.3088. Min Act: -0.0000

Data Index: 1631535 (The Pile)

Max Activating Token Index: 114

Text #11

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.2872. Min Act: -0.0000

Data Index: 1325306 (The Pile)

Max Activating Token Index: 124

Text #12

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.2795. Min Act: -0.0000

Data Index: 1181028 (The Pile)

Max Activating Token Index: 550

Text #13

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.3042. Min Act: -0.0000

Data Index: 1527802 (The Pile)

Max Activating Token Index: 265

Text #14

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.2945. Min Act: -0.0000

Data Index: 1572933 (The Pile)

Max Activating Token Index: 643

Text #15

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.2902. Min Act: -0.0000

Data Index: 951022 (The Pile)

Max Activating Token Index: 42

Text #16

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.2767. Min Act: -0.0000

Data Index: 23534 (The Pile)

Max Activating Token Index: 587

Text #17

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.2649. Min Act: -0.0000

Data Index: 1661516 (The Pile)

Max Activating Token Index: 307

Text #18

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.2578. Min Act: -0.0000

Data Index: 1783677 (The Pile)

Max Activating Token Index: 826

Text #19

Max Range: 0.5150. Min Range: -0.5150

Max Act: 0.2767. Min Act: -0.0000

Data Index: 183261 (The Pile)

Max Activating Token Index: 285