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

Dataset: The Pile

Neuron 526 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: 0.7382. Min Range: -0.7382

Max Act: 0.7382. Min Act: -0.0000

Data Index: 531120 (The Pile)

Max Activating Token Index: 861

Text #1

Max Range: 0.7382. Min Range: -0.7382

Max Act: 0.7325. Min Act: -0.0000

Data Index: 577123 (The Pile)

Max Activating Token Index: 711

Text #2

Max Range: 0.7382. Min Range: -0.7382

Max Act: 0.6948. Min Act: -0.0000

Data Index: 1170441 (The Pile)

Max Activating Token Index: 756

Text #3

Max Range: 0.7382. Min Range: -0.7382

Max Act: 0.5482. Min Act: -0.0000

Data Index: 1359281 (The Pile)

Max Activating Token Index: 927

Text #4

Max Range: 0.7382. Min Range: -0.7382

Max Act: 0.5576. Min Act: -0.0000

Data Index: 185777 (The Pile)

Max Activating Token Index: 844

Text #5

Max Range: 0.7382. Min Range: -0.7382

Max Act: 0.5610. Min Act: -0.0000

Data Index: 944905 (The Pile)

Max Activating Token Index: 145

Text #6

Max Range: 0.7382. Min Range: -0.7382

Max Act: 0.5337. Min Act: -0.0000

Data Index: 1581331 (The Pile)

Max Activating Token Index: 819

Text #7

Max Range: 0.7382. Min Range: -0.7382

Max Act: 0.5692. Min Act: -0.0000

Data Index: 282440 (The Pile)

Max Activating Token Index: 766

Text #8

Max Range: 0.7382. Min Range: -0.7382

Max Act: 0.5307. Min Act: -0.0000

Data Index: 1493018 (The Pile)

Max Activating Token Index: 960

Text #9

Max Range: 0.7382. Min Range: -0.7382

Max Act: 0.5411. Min Act: -0.0000

Data Index: 1760339 (The Pile)

Max Activating Token Index: 178

Text #10

Max Range: 0.7382. Min Range: -0.7382

Max Act: 0.4767. Min Act: -0.0000

Data Index: 238023 (The Pile)

Max Activating Token Index: 870

Text #11

Max Range: 0.7382. Min Range: -0.7382

Max Act: 0.4867. Min Act: -0.0000

Data Index: 552499 (The Pile)

Max Activating Token Index: 120

Text #12

Max Range: 0.7382. Min Range: -0.7382

Max Act: 0.5176. Min Act: -0.0000

Data Index: 987037 (The Pile)

Max Activating Token Index: 233

Text #13

Max Range: 0.7382. Min Range: -0.7382

Max Act: 0.4676. Min Act: -0.0000

Data Index: 1969050 (The Pile)

Max Activating Token Index: 404

Text #14

Max Range: 0.7382. Min Range: -0.7382

Max Act: 0.4537. Min Act: -0.0000

Data Index: 1689187 (The Pile)

Max Activating Token Index: 841

Text #15

Max Range: 0.7382. Min Range: -0.7382

Max Act: 0.4836. Min Act: -0.0000

Data Index: 695332 (The Pile)

Max Activating Token Index: 222

Text #16

Max Range: 0.7382. Min Range: -0.7382

Max Act: 0.4622. Min Act: -0.0000

Data Index: 796021 (The Pile)

Max Activating Token Index: 817

Text #17

Max Range: 0.7382. Min Range: -0.7382

Max Act: 0.4572. Min Act: -0.0000

Data Index: 1778946 (The Pile)

Max Activating Token Index: 796

Text #18

Max Range: 0.7382. Min Range: -0.7382

Max Act: 0.4988. Min Act: -0.0000

Data Index: 476837 (The Pile)

Max Activating Token Index: 40

Text #19

Max Range: 0.7382. Min Range: -0.7382

Max Act: 0.4691. Min Act: -0.0000

Data Index: 993472 (The Pile)

Max Activating Token Index: 209