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

Dataset: The Pile

Neuron 4033 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8923. Min Range: -3.8923

Max Act: 3.6777. Min Act: -0.0000

Data Index: 1422393 (The Pile)

Max Activating Token Index: 820

Text #1

Max Range: 3.8923. Min Range: -3.8923

Max Act: 3.8923. Min Act: -0.0000

Data Index: 508193 (The Pile)

Max Activating Token Index: 724

Text #2

Max Range: 3.8923. Min Range: -3.8923

Max Act: 3.2930. Min Act: -0.0000

Data Index: 87240 (The Pile)

Max Activating Token Index: 585

Text #3

Max Range: 3.8923. Min Range: -3.8923

Max Act: 3.1995. Min Act: -0.0000

Data Index: 22846 (The Pile)

Max Activating Token Index: 622

Text #4

Max Range: 3.8923. Min Range: -3.8923

Max Act: 3.0171. Min Act: -0.0000

Data Index: 464460 (The Pile)

Max Activating Token Index: 630

Text #5

Max Range: 3.8923. Min Range: -3.8923

Max Act: 2.3329. Min Act: -0.0000

Data Index: 613382 (The Pile)

Max Activating Token Index: 1014

Text #6

Max Range: 3.8923. Min Range: -3.8923

Max Act: 3.1220. Min Act: -0.0000

Data Index: 1951587 (The Pile)

Max Activating Token Index: 617

Text #7

Max Range: 3.8923. Min Range: -3.8923

Max Act: 2.9007. Min Act: -0.0000

Data Index: 1642739 (The Pile)

Max Activating Token Index: 654

Text #8

Max Range: 3.8923. Min Range: -3.8923

Max Act: 2.5760. Min Act: -0.0000

Data Index: 510502 (The Pile)

Max Activating Token Index: 573

Text #9

Max Range: 3.8923. Min Range: -3.8923

Max Act: 2.6120. Min Act: -0.0000

Data Index: 1764083 (The Pile)

Max Activating Token Index: 109

Text #10

Max Range: 3.8923. Min Range: -3.8923

Max Act: 2.6948. Min Act: -0.0000

Data Index: 1075130 (The Pile)

Max Activating Token Index: 795

Text #11

Max Range: 3.8923. Min Range: -3.8923

Max Act: 2.8769. Min Act: -0.0000

Data Index: 287621 (The Pile)

Max Activating Token Index: 716

Text #12

Max Range: 3.8923. Min Range: -3.8923

Max Act: 2.0052. Min Act: -0.0000

Data Index: 841959 (The Pile)

Max Activating Token Index: 575

Text #13

Max Range: 3.8923. Min Range: -3.8923

Max Act: 2.4575. Min Act: -0.0000

Data Index: 1104283 (The Pile)

Max Activating Token Index: 90

Text #14

Max Range: 3.8923. Min Range: -3.8923

Max Act: 2.2463. Min Act: -0.0000

Data Index: 1199238 (The Pile)

Max Activating Token Index: 719

Text #15

Max Range: 3.8923. Min Range: -3.8923

Max Act: 1.9904. Min Act: -0.0000

Data Index: 486844 (The Pile)

Max Activating Token Index: 575

Text #16

Max Range: 3.8923. Min Range: -3.8923

Max Act: 2.4711. Min Act: -0.0000

Data Index: 70047 (The Pile)

Max Activating Token Index: 498

Text #17

Max Range: 3.8923. Min Range: -3.8923

Max Act: 2.4684. Min Act: -0.0000

Data Index: 1926283 (The Pile)

Max Activating Token Index: 559

Text #18

Max Range: 3.8923. Min Range: -3.8923

Max Act: 2.4297. Min Act: -0.0000

Data Index: 116339 (The Pile)

Max Activating Token Index: 331

Text #19

Max Range: 3.8923. Min Range: -3.8923

Max Act: 2.7364. Min Act: -0.0000

Data Index: 1609228 (The Pile)

Max Activating Token Index: 254