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

Dataset: The Pile

Neuron 1437 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: 0.5142. Min Range: -0.5142

Max Act: 0.5142. Min Act: -0.0000

Data Index: 1152145 (The Pile)

Max Activating Token Index: 637

Text #1

Max Range: 0.5142. Min Range: -0.5142

Max Act: 0.3300. Min Act: -0.0000

Data Index: 341572 (The Pile)

Max Activating Token Index: 488

Text #2

Max Range: 0.5142. Min Range: -0.5142

Max Act: 0.2839. Min Act: -0.0000

Data Index: 1445044 (The Pile)

Max Activating Token Index: 413

Text #3

Max Range: 0.5142. Min Range: -0.5142

Max Act: 0.2947. Min Act: -0.0000

Data Index: 1307247 (The Pile)

Max Activating Token Index: 388

Text #4

Max Range: 0.5142. Min Range: -0.5142

Max Act: 0.2801. Min Act: -0.0000

Data Index: 1306520 (The Pile)

Max Activating Token Index: 533

Text #5

Max Range: 0.5142. Min Range: -0.5142

Max Act: 0.2672. Min Act: -0.0000

Data Index: 352610 (The Pile)

Max Activating Token Index: 794

Text #6

Max Range: 0.5142. Min Range: -0.5142

Max Act: 0.2625. Min Act: -0.0000

Data Index: 314402 (The Pile)

Max Activating Token Index: 87

Text #7

Max Range: 0.5142. Min Range: -0.5142

Max Act: 0.2557. Min Act: -0.0000

Data Index: 1703481 (The Pile)

Max Activating Token Index: 8

Text #8

Max Range: 0.5142. Min Range: -0.5142

Max Act: 0.2840. Min Act: -0.0000

Data Index: 46976 (The Pile)

Max Activating Token Index: 904

Text #9

Max Range: 0.5142. Min Range: -0.5142

Max Act: 0.2331. Min Act: -0.0000

Data Index: 128141 (The Pile)

Max Activating Token Index: 1021

Text #10

Max Range: 0.5142. Min Range: -0.5142

Max Act: 0.2433. Min Act: -0.0000

Data Index: 716876 (The Pile)

Max Activating Token Index: 430

Text #11

Max Range: 0.5142. Min Range: -0.5142

Max Act: 0.2743. Min Act: -0.0000

Data Index: 983764 (The Pile)

Max Activating Token Index: 196

Text #12

Max Range: 0.5142. Min Range: -0.5142

Max Act: 0.2579. Min Act: -0.0000

Data Index: 215758 (The Pile)

Max Activating Token Index: 1006

Text #13

Max Range: 0.5142. Min Range: -0.5142

Max Act: 0.2553. Min Act: -0.0000

Data Index: 1171933 (The Pile)

Max Activating Token Index: 518

Text #14

Max Range: 0.5142. Min Range: -0.5142

Max Act: 0.2683. Min Act: -0.0000

Data Index: 1247042 (The Pile)

Max Activating Token Index: 1010

Text #15

Max Range: 0.5142. Min Range: -0.5142

Max Act: 0.2425. Min Act: -0.0000

Data Index: 1626844 (The Pile)

Max Activating Token Index: 89

Text #16

Max Range: 0.5142. Min Range: -0.5142

Max Act: 0.2182. Min Act: -0.0000

Data Index: 183933 (The Pile)

Max Activating Token Index: 870

Text #17

Max Range: 0.5142. Min Range: -0.5142

Max Act: 0.2263. Min Act: -0.0000

Data Index: 896829 (The Pile)

Max Activating Token Index: 71

Text #18

Max Range: 0.5142. Min Range: -0.5142

Max Act: 0.2682. Min Act: -0.0000

Data Index: 1076284 (The Pile)

Max Activating Token Index: 992

Text #19

Max Range: 0.5142. Min Range: -0.5142

Max Act: 0.2326. Min Act: -0.0000

Data Index: 794988 (The Pile)

Max Activating Token Index: 370