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

Dataset: The Pile

Neuron 1685 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: 0.2384. Min Range: -0.2384

Max Act: 0.2350. Min Act: -0.0000

Data Index: 388423 (The Pile)

Max Activating Token Index: 948

Text #1

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.2285. Min Act: -0.0000

Data Index: 553585 (The Pile)

Max Activating Token Index: 237

Text #2

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.2303. Min Act: -0.0000

Data Index: 426784 (The Pile)

Max Activating Token Index: 940

Text #3

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.2376. Min Act: -0.0000

Data Index: 493678 (The Pile)

Max Activating Token Index: 781

Text #4

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.2048. Min Act: -0.0000

Data Index: 1080878 (The Pile)

Max Activating Token Index: 402

Text #5

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1985. Min Act: -0.0000

Data Index: 1466117 (The Pile)

Max Activating Token Index: 484

Text #6

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.2266. Min Act: -0.0000

Data Index: 847290 (The Pile)

Max Activating Token Index: 260

Text #7

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.2027. Min Act: -0.0000

Data Index: 320713 (The Pile)

Max Activating Token Index: 675

Text #8

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.2032. Min Act: -0.0000

Data Index: 1860651 (The Pile)

Max Activating Token Index: 459

Text #9

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.2090. Min Act: -0.0000

Data Index: 1918259 (The Pile)

Max Activating Token Index: 194

Text #10

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1836. Min Act: -0.0000

Data Index: 1251824 (The Pile)

Max Activating Token Index: 257

Text #11

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1886. Min Act: -0.0000

Data Index: 1194102 (The Pile)

Max Activating Token Index: 742

Text #12

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.2062. Min Act: -0.0000

Data Index: 135541 (The Pile)

Max Activating Token Index: 248

Text #13

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1969. Min Act: -0.0000

Data Index: 350820 (The Pile)

Max Activating Token Index: 292

Text #14

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1742. Min Act: -0.0000

Data Index: 345999 (The Pile)

Max Activating Token Index: 1005

Text #15

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.2169. Min Act: -0.0000

Data Index: 275852 (The Pile)

Max Activating Token Index: 200

Text #16

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1766. Min Act: -0.0000

Data Index: 1671725 (The Pile)

Max Activating Token Index: 45

Text #17

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1865. Min Act: -0.0000

Data Index: 285266 (The Pile)

Max Activating Token Index: 256

Text #18

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.1943. Min Act: -0.0000

Data Index: 1828391 (The Pile)

Max Activating Token Index: 224

Text #19

Max Range: 0.2384. Min Range: -0.2384

Max Act: 0.2384. Min Act: -0.0000

Data Index: 1044973 (The Pile)

Max Activating Token Index: 763