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

Dataset: The Pile

Neuron 1981 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: 0.4816. Min Range: -0.4816

Max Act: 0.4816. Min Act: -0.0000

Data Index: 937154 (The Pile)

Max Activating Token Index: 952

Text #1

Max Range: 0.4816. Min Range: -0.4816

Max Act: 0.4331. Min Act: -0.0000

Data Index: 91803 (The Pile)

Max Activating Token Index: 494

Text #2

Max Range: 0.4816. Min Range: -0.4816

Max Act: 0.4338. Min Act: -0.0000

Data Index: 1936259 (The Pile)

Max Activating Token Index: 483

Text #3

Max Range: 0.4816. Min Range: -0.4816

Max Act: 0.4392. Min Act: -0.0000

Data Index: 73774 (The Pile)

Max Activating Token Index: 490

Text #4

Max Range: 0.4816. Min Range: -0.4816

Max Act: 0.4020. Min Act: -0.0000

Data Index: 692936 (The Pile)

Max Activating Token Index: 211

Text #5

Max Range: 0.4816. Min Range: -0.4816

Max Act: 0.3807. Min Act: -0.0000

Data Index: 1992152 (The Pile)

Max Activating Token Index: 188

Text #6

Max Range: 0.4816. Min Range: -0.4816

Max Act: 0.4191. Min Act: -0.0000

Data Index: 1954745 (The Pile)

Max Activating Token Index: 132

Text #7

Max Range: 0.4816. Min Range: -0.4816

Max Act: 0.3915. Min Act: -0.0000

Data Index: 737467 (The Pile)

Max Activating Token Index: 416

Text #8

Max Range: 0.4816. Min Range: -0.4816

Max Act: 0.4135. Min Act: -0.0000

Data Index: 1573122 (The Pile)

Max Activating Token Index: 351

Text #9

Max Range: 0.4816. Min Range: -0.4816

Max Act: 0.3874. Min Act: -0.0000

Data Index: 611116 (The Pile)

Max Activating Token Index: 264

Text #10

Max Range: 0.4816. Min Range: -0.4816

Max Act: 0.3888. Min Act: -0.0000

Data Index: 1473049 (The Pile)

Max Activating Token Index: 567

Text #11

Max Range: 0.4816. Min Range: -0.4816

Max Act: 0.3943. Min Act: -0.0000

Data Index: 644085 (The Pile)

Max Activating Token Index: 69

Text #12

Max Range: 0.4816. Min Range: -0.4816

Max Act: 0.3910. Min Act: -0.0000

Data Index: 1327778 (The Pile)

Max Activating Token Index: 448

Text #13

Max Range: 0.4816. Min Range: -0.4816

Max Act: 0.3845. Min Act: -0.0000

Data Index: 882097 (The Pile)

Max Activating Token Index: 163

Text #14

Max Range: 0.4816. Min Range: -0.4816

Max Act: 0.3920. Min Act: -0.0000

Data Index: 1859503 (The Pile)

Max Activating Token Index: 610

Text #15

Max Range: 0.4816. Min Range: -0.4816

Max Act: 0.3885. Min Act: -0.0000

Data Index: 820975 (The Pile)

Max Activating Token Index: 268

Text #16

Max Range: 0.4816. Min Range: -0.4816

Max Act: 0.3816. Min Act: -0.0000

Data Index: 618030 (The Pile)

Max Activating Token Index: 546

Text #17

Max Range: 0.4816. Min Range: -0.4816

Max Act: 0.3732. Min Act: -0.0000

Data Index: 1031798 (The Pile)

Max Activating Token Index: 402

Text #18

Max Range: 0.4816. Min Range: -0.4816

Max Act: 0.3720. Min Act: -0.0000

Data Index: 578626 (The Pile)

Max Activating Token Index: 157

Text #19

Max Range: 0.4816. Min Range: -0.4816

Max Act: 0.3617. Min Act: -0.0000

Data Index: 1548107 (The Pile)

Max Activating Token Index: 356