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

Dataset: The Pile

Neuron 2040 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: 0.4277. Min Range: -0.4277

Max Act: 0.4277. Min Act: -0.0000

Data Index: 656799 (The Pile)

Max Activating Token Index: 16

Text #1

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.3668. Min Act: -0.0000

Data Index: 945339 (The Pile)

Max Activating Token Index: 97

Text #2

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.3324. Min Act: -0.0000

Data Index: 100632 (The Pile)

Max Activating Token Index: 584

Text #3

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.3176. Min Act: -0.0000

Data Index: 1696595 (The Pile)

Max Activating Token Index: 60

Text #4

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.3031. Min Act: -0.0000

Data Index: 202994 (The Pile)

Max Activating Token Index: 346

Text #5

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.2904. Min Act: -0.0000

Data Index: 622359 (The Pile)

Max Activating Token Index: 262

Text #6

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.3062. Min Act: -0.0000

Data Index: 1187464 (The Pile)

Max Activating Token Index: 653

Text #7

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.2725. Min Act: -0.0000

Data Index: 1268538 (The Pile)

Max Activating Token Index: 540

Text #8

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.2900. Min Act: -0.0000

Data Index: 374155 (The Pile)

Max Activating Token Index: 728

Text #9

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.2787. Min Act: -0.0000

Data Index: 719620 (The Pile)

Max Activating Token Index: 350

Text #10

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.2504. Min Act: -0.0000

Data Index: 1671866 (The Pile)

Max Activating Token Index: 112

Text #11

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.2742. Min Act: -0.0000

Data Index: 324355 (The Pile)

Max Activating Token Index: 131

Text #12

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.2714. Min Act: -0.0000

Data Index: 1254391 (The Pile)

Max Activating Token Index: 552

Text #13

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.2710. Min Act: -0.0000

Data Index: 1450863 (The Pile)

Max Activating Token Index: 739

Text #14

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.2811. Min Act: -0.0000

Data Index: 1384569 (The Pile)

Max Activating Token Index: 473

Text #15

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.2645. Min Act: -0.0000

Data Index: 1755984 (The Pile)

Max Activating Token Index: 120

Text #16

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.2471. Min Act: -0.0000

Data Index: 226735 (The Pile)

Max Activating Token Index: 272

Text #17

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.2504. Min Act: -0.0000

Data Index: 553367 (The Pile)

Max Activating Token Index: 938

Text #18

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.2580. Min Act: -0.0000

Data Index: 1247610 (The Pile)

Max Activating Token Index: 503

Text #19

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.2595. Min Act: -0.0000

Data Index: 1306818 (The Pile)

Max Activating Token Index: 76