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

Dataset: The Pile

Neuron 1604 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: 5.3212. Min Range: -5.3212

Max Act: 5.3212. Min Act: -0.0000

Data Index: 777104 (The Pile)

Max Activating Token Index: 452

Text #1

Max Range: 5.3212. Min Range: -5.3212

Max Act: 4.4667. Min Act: -0.0000

Data Index: 1240134 (The Pile)

Max Activating Token Index: 35

Text #2

Max Range: 5.3212. Min Range: -5.3212

Max Act: 4.6307. Min Act: -0.0000

Data Index: 1364757 (The Pile)

Max Activating Token Index: 105

Text #3

Max Range: 5.3212. Min Range: -5.3212

Max Act: 3.9408. Min Act: -0.0000

Data Index: 1817217 (The Pile)

Max Activating Token Index: 536

Text #4

Max Range: 5.3212. Min Range: -5.3212

Max Act: 4.4296. Min Act: -0.0000

Data Index: 397817 (The Pile)

Max Activating Token Index: 828

Text #5

Max Range: 5.3212. Min Range: -5.3212

Max Act: 4.4417. Min Act: -0.0000

Data Index: 1292987 (The Pile)

Max Activating Token Index: 706

Text #6

Max Range: 5.3212. Min Range: -5.3212

Max Act: 3.6292. Min Act: -0.0000

Data Index: 1220990 (The Pile)

Max Activating Token Index: 447

Text #7

Max Range: 5.3212. Min Range: -5.3212

Max Act: 3.7642. Min Act: -0.0000

Data Index: 852537 (The Pile)

Max Activating Token Index: 974

Text #8

Max Range: 5.3212. Min Range: -5.3212

Max Act: 3.6641. Min Act: -0.0000

Data Index: 1117821 (The Pile)

Max Activating Token Index: 803

Text #9

Max Range: 5.3212. Min Range: -5.3212

Max Act: 3.6789. Min Act: -0.0000

Data Index: 1276018 (The Pile)

Max Activating Token Index: 995

Text #10

Max Range: 5.3212. Min Range: -5.3212

Max Act: 3.6158. Min Act: -0.0000

Data Index: 524345 (The Pile)

Max Activating Token Index: 368

Text #11

Max Range: 5.3212. Min Range: -5.3212

Max Act: 3.2958. Min Act: -0.0000

Data Index: 1052311 (The Pile)

Max Activating Token Index: 475

Text #12

Max Range: 5.3212. Min Range: -5.3212

Max Act: 3.6183. Min Act: -0.0000

Data Index: 1421711 (The Pile)

Max Activating Token Index: 964

Text #13

Max Range: 5.3212. Min Range: -5.3212

Max Act: 3.5500. Min Act: -0.0000

Data Index: 1746304 (The Pile)

Max Activating Token Index: 31

Text #14

Max Range: 5.3212. Min Range: -5.3212

Max Act: 3.5383. Min Act: -0.0000

Data Index: 1901788 (The Pile)

Max Activating Token Index: 424

Text #15

Max Range: 5.3212. Min Range: -5.3212

Max Act: 3.6831. Min Act: -0.0000

Data Index: 1154235 (The Pile)

Max Activating Token Index: 501

Text #16

Max Range: 5.3212. Min Range: -5.3212

Max Act: 4.0027. Min Act: -0.0000

Data Index: 1195652 (The Pile)

Max Activating Token Index: 651

Text #17

Max Range: 5.3212. Min Range: -5.3212

Max Act: 3.4815. Min Act: -0.0000

Data Index: 1541979 (The Pile)

Max Activating Token Index: 405

Text #18

Max Range: 5.3212. Min Range: -5.3212

Max Act: 3.3283. Min Act: -0.0000

Data Index: 1345710 (The Pile)

Max Activating Token Index: 684

Text #19

Max Range: 5.3212. Min Range: -5.3212

Max Act: 3.3105. Min Act: -0.0000

Data Index: 1479501 (The Pile)

Max Activating Token Index: 591