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

Dataset: The Pile

Neuron 1186 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: 0.8431. Min Range: -0.8431

Max Act: 0.8431. Min Act: -0.0000

Data Index: 456114 (The Pile)

Max Activating Token Index: 854

Text #1

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.8020. Min Act: -0.0000

Data Index: 1587839 (The Pile)

Max Activating Token Index: 658

Text #2

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.8061. Min Act: -0.0000

Data Index: 1709 (The Pile)

Max Activating Token Index: 504

Text #3

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.7533. Min Act: 0.0000

Data Index: 813976 (The Pile)

Max Activating Token Index: 73

Text #4

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.8061. Min Act: -0.0000

Data Index: 855140 (The Pile)

Max Activating Token Index: 153

Text #5

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.7680. Min Act: 0.0000

Data Index: 939673 (The Pile)

Max Activating Token Index: 154

Text #6

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.7240. Min Act: 0.0000

Data Index: 1024196 (The Pile)

Max Activating Token Index: 216

Text #7

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.7225. Min Act: -0.0000

Data Index: 122576 (The Pile)

Max Activating Token Index: 601

Text #8

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.6901. Min Act: -0.0000

Data Index: 1154966 (The Pile)

Max Activating Token Index: 883

Text #9

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.6868. Min Act: -0.0000

Data Index: 985502 (The Pile)

Max Activating Token Index: 939

Text #10

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.6848. Min Act: -0.0000

Data Index: 1169396 (The Pile)

Max Activating Token Index: 144

Text #11

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.6702. Min Act: -0.0000

Data Index: 39225 (The Pile)

Max Activating Token Index: 577

Text #12

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.6702. Min Act: -0.0000

Data Index: 419809 (The Pile)

Max Activating Token Index: 460

Text #13

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.6600. Min Act: -0.0000

Data Index: 1613598 (The Pile)

Max Activating Token Index: 180

Text #14

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.6786. Min Act: -0.0000

Data Index: 767831 (The Pile)

Max Activating Token Index: 299

Text #15

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.6793. Min Act: -0.0000

Data Index: 753280 (The Pile)

Max Activating Token Index: 517

Text #16

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.6733. Min Act: -0.0000

Data Index: 1092386 (The Pile)

Max Activating Token Index: 205

Text #17

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.6835. Min Act: -0.0000

Data Index: 1659115 (The Pile)

Max Activating Token Index: 200

Text #18

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.6729. Min Act: -0.0000

Data Index: 406133 (The Pile)

Max Activating Token Index: 390

Text #19

Max Range: 0.8431. Min Range: -0.8431

Max Act: 0.6300. Min Act: -0.0000

Data Index: 748264 (The Pile)

Max Activating Token Index: 126