Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3881 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5959. Min Range: -0.5959

Max Act: 0.5907. Min Act: -0.0000

Data Index: 1804740 (The Pile)

Max Activating Token Index: 722

Text #1

Max Range: 0.5959. Min Range: -0.5959

Max Act: 0.5959. Min Act: -0.0000

Data Index: 1879695 (The Pile)

Max Activating Token Index: 983

Text #2

Max Range: 0.5959. Min Range: -0.5959

Max Act: 0.5760. Min Act: -0.0000

Data Index: 510714 (The Pile)

Max Activating Token Index: 460

Text #3

Max Range: 0.5959. Min Range: -0.5959

Max Act: 0.5852. Min Act: -0.0000

Data Index: 309525 (The Pile)

Max Activating Token Index: 104

Text #4

Max Range: 0.5959. Min Range: -0.5959

Max Act: 0.5447. Min Act: -0.0000

Data Index: 1275664 (The Pile)

Max Activating Token Index: 295

Text #5

Max Range: 0.5959. Min Range: -0.5959

Max Act: 0.5085. Min Act: -0.0000

Data Index: 1521660 (The Pile)

Max Activating Token Index: 459

Text #6

Max Range: 0.5959. Min Range: -0.5959

Max Act: 0.5475. Min Act: -0.0000

Data Index: 1227000 (The Pile)

Max Activating Token Index: 369

Text #7

Max Range: 0.5959. Min Range: -0.5959

Max Act: 0.5558. Min Act: -0.0000

Data Index: 947939 (The Pile)

Max Activating Token Index: 603

Text #8

Max Range: 0.5959. Min Range: -0.5959

Max Act: 0.5308. Min Act: -0.0000

Data Index: 875132 (The Pile)

Max Activating Token Index: 363

Text #9

Max Range: 0.5959. Min Range: -0.5959

Max Act: 0.5538. Min Act: -0.0000

Data Index: 1689837 (The Pile)

Max Activating Token Index: 991

Text #10

Max Range: 0.5959. Min Range: -0.5959

Max Act: 0.5387. Min Act: -0.0000

Data Index: 963705 (The Pile)

Max Activating Token Index: 528

Text #11

Max Range: 0.5959. Min Range: -0.5959

Max Act: 0.5657. Min Act: -0.0000

Data Index: 763462 (The Pile)

Max Activating Token Index: 634

Text #12

Max Range: 0.5959. Min Range: -0.5959

Max Act: 0.5269. Min Act: -0.0000

Data Index: 1640067 (The Pile)

Max Activating Token Index: 460

Text #13

Max Range: 0.5959. Min Range: -0.5959

Max Act: 0.4989. Min Act: -0.0000

Data Index: 1530508 (The Pile)

Max Activating Token Index: 416

Text #14

Max Range: 0.5959. Min Range: -0.5959

Max Act: 0.5081. Min Act: -0.0000

Data Index: 204099 (The Pile)

Max Activating Token Index: 734

Text #15

Max Range: 0.5959. Min Range: -0.5959

Max Act: 0.4866. Min Act: -0.0000

Data Index: 903252 (The Pile)

Max Activating Token Index: 773

Text #16

Max Range: 0.5959. Min Range: -0.5959

Max Act: 0.4489. Min Act: -0.0000

Data Index: 985280 (The Pile)

Max Activating Token Index: 896

Text #17

Max Range: 0.5959. Min Range: -0.5959

Max Act: 0.4964. Min Act: -0.0000

Data Index: 285431 (The Pile)

Max Activating Token Index: 292

Text #18

Max Range: 0.5959. Min Range: -0.5959

Max Act: 0.4598. Min Act: -0.0000

Data Index: 1958751 (The Pile)

Max Activating Token Index: 588

Text #19

Max Range: 0.5959. Min Range: -0.5959

Max Act: 0.4882. Min Act: -0.0000

Data Index: 1223442 (The Pile)

Max Activating Token Index: 720