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

Dataset: The Pile

Neuron 125 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5178. Min Range: -1.5178

Max Act: 1.5178. Min Act: -0.0000

Data Index: 1889445 (The Pile)

Max Activating Token Index: 123

Text #1

Max Range: 1.5178. Min Range: -1.5178

Max Act: 1.4263. Min Act: -0.0000

Data Index: 1964847 (The Pile)

Max Activating Token Index: 743

Text #2

Max Range: 1.5178. Min Range: -1.5178

Max Act: 1.2570. Min Act: -0.0000

Data Index: 1706284 (The Pile)

Max Activating Token Index: 546

Text #3

Max Range: 1.5178. Min Range: -1.5178

Max Act: 1.1290. Min Act: -0.0000

Data Index: 1315955 (The Pile)

Max Activating Token Index: 612

Text #4

Max Range: 1.5178. Min Range: -1.5178

Max Act: 1.1477. Min Act: -0.0000

Data Index: 1439915 (The Pile)

Max Activating Token Index: 541

Text #5

Max Range: 1.5178. Min Range: -1.5178

Max Act: 1.0835. Min Act: -0.0000

Data Index: 584215 (The Pile)

Max Activating Token Index: 94

Text #6

Max Range: 1.5178. Min Range: -1.5178

Max Act: 1.1694. Min Act: -0.0000

Data Index: 1841675 (The Pile)

Max Activating Token Index: 162

Text #7

Max Range: 1.5178. Min Range: -1.5178

Max Act: 1.0989. Min Act: -0.0000

Data Index: 1991206 (The Pile)

Max Activating Token Index: 807

Text #8

Max Range: 1.5178. Min Range: -1.5178

Max Act: 1.0640. Min Act: -0.0000

Data Index: 1554018 (The Pile)

Max Activating Token Index: 12

Text #9

Max Range: 1.5178. Min Range: -1.5178

Max Act: 1.0800. Min Act: -0.0000

Data Index: 1720104 (The Pile)

Max Activating Token Index: 621

Text #10

Max Range: 1.5178. Min Range: -1.5178

Max Act: 1.0266. Min Act: -0.0000

Data Index: 371787 (The Pile)

Max Activating Token Index: 83

Text #11

Max Range: 1.5178. Min Range: -1.5178

Max Act: 0.9942. Min Act: -0.0000

Data Index: 1547102 (The Pile)

Max Activating Token Index: 500

Text #12

Max Range: 1.5178. Min Range: -1.5178

Max Act: 1.0243. Min Act: -0.0000

Data Index: 1948111 (The Pile)

Max Activating Token Index: 868

Text #13

Max Range: 1.5178. Min Range: -1.5178

Max Act: 0.9860. Min Act: -0.0000

Data Index: 203900 (The Pile)

Max Activating Token Index: 563

Text #14

Max Range: 1.5178. Min Range: -1.5178

Max Act: 0.9538. Min Act: -0.0000

Data Index: 1755259 (The Pile)

Max Activating Token Index: 215

Text #15

Max Range: 1.5178. Min Range: -1.5178

Max Act: 0.9471. Min Act: -0.0000

Data Index: 307733 (The Pile)

Max Activating Token Index: 898

Text #16

Max Range: 1.5178. Min Range: -1.5178

Max Act: 0.9136. Min Act: -0.0000

Data Index: 488609 (The Pile)

Max Activating Token Index: 571

Text #17

Max Range: 1.5178. Min Range: -1.5178

Max Act: 1.0063. Min Act: -0.0000

Data Index: 1145656 (The Pile)

Max Activating Token Index: 163

Text #18

Max Range: 1.5178. Min Range: -1.5178

Max Act: 1.0638. Min Act: -0.0000

Data Index: 1293286 (The Pile)

Max Activating Token Index: 654

Text #19

Max Range: 1.5178. Min Range: -1.5178

Max Act: 0.8818. Min Act: -0.0000

Data Index: 1943370 (The Pile)

Max Activating Token Index: 149