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

Dataset: The Pile

Neuron 2633 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.2874. Min Act: -0.0000

Data Index: 330964 (The Pile)

Max Activating Token Index: 128

Text #1

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.2823. Min Act: -0.0000

Data Index: 353470 (The Pile)

Max Activating Token Index: 390

Text #2

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.2678. Min Act: -0.0000

Data Index: 1998863 (The Pile)

Max Activating Token Index: 34

Text #3

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.2586. Min Act: -0.0000

Data Index: 1528066 (The Pile)

Max Activating Token Index: 259

Text #4

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.2601. Min Act: -0.0000

Data Index: 1019622 (The Pile)

Max Activating Token Index: 180

Text #5

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.2462. Min Act: -0.0000

Data Index: 1288759 (The Pile)

Max Activating Token Index: 34

Text #6

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.2360. Min Act: -0.0000

Data Index: 908628 (The Pile)

Max Activating Token Index: 282

Text #7

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.2423. Min Act: -0.0000

Data Index: 1257436 (The Pile)

Max Activating Token Index: 519

Text #8

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.2402. Min Act: -0.0000

Data Index: 572604 (The Pile)

Max Activating Token Index: 704

Text #9

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.2532. Min Act: -0.0000

Data Index: 372658 (The Pile)

Max Activating Token Index: 982

Text #10

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.2358. Min Act: -0.0000

Data Index: 623665 (The Pile)

Max Activating Token Index: 569

Text #11

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.2323. Min Act: -0.0000

Data Index: 455602 (The Pile)

Max Activating Token Index: 273

Text #12

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.2280. Min Act: -0.0000

Data Index: 1636882 (The Pile)

Max Activating Token Index: 143

Text #13

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.2294. Min Act: -0.0000

Data Index: 1160413 (The Pile)

Max Activating Token Index: 73

Text #14

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.2210. Min Act: -0.0000

Data Index: 613818 (The Pile)

Max Activating Token Index: 834

Text #15

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.2199. Min Act: -0.0000

Data Index: 640348 (The Pile)

Max Activating Token Index: 994

Text #16

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.2192. Min Act: -0.0000

Data Index: 1393836 (The Pile)

Max Activating Token Index: 439

Text #17

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.2245. Min Act: -0.0000

Data Index: 1775212 (The Pile)

Max Activating Token Index: 747

Text #18

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.2180. Min Act: -0.0000

Data Index: 1224628 (The Pile)

Max Activating Token Index: 508

Text #19

Max Range: 0.2874. Min Range: -0.2874

Max Act: 0.2283. Min Act: -0.0000

Data Index: 72939 (The Pile)

Max Activating Token Index: 739