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

Dataset: The Pile

Neuron 2983 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.5111. Min Act: -0.0000

Data Index: 338051 (The Pile)

Max Activating Token Index: 151

Text #1

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.3547. Min Act: -0.0000

Data Index: 1295795 (The Pile)

Max Activating Token Index: 361

Text #2

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.3450. Min Act: -0.0000

Data Index: 971257 (The Pile)

Max Activating Token Index: 659

Text #3

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.3373. Min Act: 0.0000

Data Index: 1339352 (The Pile)

Max Activating Token Index: 252

Text #4

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.3253. Min Act: 0.0000

Data Index: 658052 (The Pile)

Max Activating Token Index: 123

Text #5

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.2989. Min Act: -0.0000

Data Index: 1060958 (The Pile)

Max Activating Token Index: 518

Text #6

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.3220. Min Act: -0.0000

Data Index: 665854 (The Pile)

Max Activating Token Index: 903

Text #7

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.3075. Min Act: -0.0000

Data Index: 654419 (The Pile)

Max Activating Token Index: 668

Text #8

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.3247. Min Act: -0.0000

Data Index: 1614717 (The Pile)

Max Activating Token Index: 752

Text #9

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.3071. Min Act: -0.0000

Data Index: 1251415 (The Pile)

Max Activating Token Index: 313

Text #10

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.3093. Min Act: -0.0000

Data Index: 1447622 (The Pile)

Max Activating Token Index: 49

Text #11

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.2984. Min Act: -0.0000

Data Index: 1490418 (The Pile)

Max Activating Token Index: 385

Text #12

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.3045. Min Act: -0.0000

Data Index: 1279550 (The Pile)

Max Activating Token Index: 665

Text #13

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.3026. Min Act: 0.0000

Data Index: 812871 (The Pile)

Max Activating Token Index: 921

Text #14

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.2986. Min Act: -0.0000

Data Index: 67811 (The Pile)

Max Activating Token Index: 475

Text #15

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.2929. Min Act: -0.0000

Data Index: 1318271 (The Pile)

Max Activating Token Index: 825

Text #16

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.3011. Min Act: -0.0000

Data Index: 1255595 (The Pile)

Max Activating Token Index: 813

Text #17

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.2785. Min Act: -0.0000

Data Index: 1784017 (The Pile)

Max Activating Token Index: 368

Text #18

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.2763. Min Act: -0.0000

Data Index: 762040 (The Pile)

Max Activating Token Index: 518

Text #19

Max Range: 0.5111. Min Range: -0.5111

Max Act: 0.2781. Min Act: -0.0000

Data Index: 513174 (The Pile)

Max Activating Token Index: 565