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

Dataset: The Pile

Neuron 4659 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: 3.3744. Min Range: -3.3744

Max Act: 3.3552. Min Act: -0.0000

Data Index: 481164 (The Pile)

Max Activating Token Index: 548

Text #1

Max Range: 3.3744. Min Range: -3.3744

Max Act: 3.3744. Min Act: -0.0000

Data Index: 669320 (The Pile)

Max Activating Token Index: 209

Text #2

Max Range: 3.3744. Min Range: -3.3744

Max Act: 2.8068. Min Act: -0.0000

Data Index: 1852855 (The Pile)

Max Activating Token Index: 320

Text #3

Max Range: 3.3744. Min Range: -3.3744

Max Act: 2.5282. Min Act: -0.0000

Data Index: 807074 (The Pile)

Max Activating Token Index: 971

Text #4

Max Range: 3.3744. Min Range: -3.3744

Max Act: 2.6932. Min Act: -0.0000

Data Index: 1991168 (The Pile)

Max Activating Token Index: 410

Text #5

Max Range: 3.3744. Min Range: -3.3744

Max Act: 2.5086. Min Act: -0.0000

Data Index: 891714 (The Pile)

Max Activating Token Index: 1006

Text #6

Max Range: 3.3744. Min Range: -3.3744

Max Act: 2.4234. Min Act: -0.0000

Data Index: 279997 (The Pile)

Max Activating Token Index: 181

Text #7

Max Range: 3.3744. Min Range: -3.3744

Max Act: 2.6879. Min Act: -0.0000

Data Index: 125685 (The Pile)

Max Activating Token Index: 68

Text #8

Max Range: 3.3744. Min Range: -3.3744

Max Act: 2.5630. Min Act: -0.0000

Data Index: 1909609 (The Pile)

Max Activating Token Index: 8

Text #9

Max Range: 3.3744. Min Range: -3.3744

Max Act: 2.3690. Min Act: -0.0000

Data Index: 1905615 (The Pile)

Max Activating Token Index: 574

Text #10

Max Range: 3.3744. Min Range: -3.3744

Max Act: 2.3728. Min Act: -0.0000

Data Index: 1196492 (The Pile)

Max Activating Token Index: 567

Text #11

Max Range: 3.3744. Min Range: -3.3744

Max Act: 2.2177. Min Act: -0.0000

Data Index: 638020 (The Pile)

Max Activating Token Index: 681

Text #12

Max Range: 3.3744. Min Range: -3.3744

Max Act: 2.3095. Min Act: -0.0000

Data Index: 1656218 (The Pile)

Max Activating Token Index: 897

Text #13

Max Range: 3.3744. Min Range: -3.3744

Max Act: 2.1703. Min Act: -0.0000

Data Index: 1452045 (The Pile)

Max Activating Token Index: 137

Text #14

Max Range: 3.3744. Min Range: -3.3744

Max Act: 2.2837. Min Act: -0.0000

Data Index: 1467933 (The Pile)

Max Activating Token Index: 231

Text #15

Max Range: 3.3744. Min Range: -3.3744

Max Act: 2.1555. Min Act: -0.0000

Data Index: 1452480 (The Pile)

Max Activating Token Index: 747

Text #16

Max Range: 3.3744. Min Range: -3.3744

Max Act: 1.8285. Min Act: -0.0000

Data Index: 606718 (The Pile)

Max Activating Token Index: 211

Text #17

Max Range: 3.3744. Min Range: -3.3744

Max Act: 1.9143. Min Act: -0.0000

Data Index: 885261 (The Pile)

Max Activating Token Index: 13

Text #18

Max Range: 3.3744. Min Range: -3.3744

Max Act: 1.9831. Min Act: -0.0000

Data Index: 674086 (The Pile)

Max Activating Token Index: 293

Text #19

Max Range: 3.3744. Min Range: -3.3744

Max Act: 2.0838. Min Act: -0.0000

Data Index: 1780872 (The Pile)

Max Activating Token Index: 501