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

Dataset: The Pile

Neuron 2111 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.6137. Min Act: -0.0000

Data Index: 671241 (The Pile)

Max Activating Token Index: 163

Text #1

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.6622. Min Act: -0.0000

Data Index: 1520536 (The Pile)

Max Activating Token Index: 331

Text #2

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.6158. Min Act: -0.0000

Data Index: 1401804 (The Pile)

Max Activating Token Index: 327

Text #3

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.6678. Min Act: -0.0000

Data Index: 573723 (The Pile)

Max Activating Token Index: 962

Text #4

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.6332. Min Act: -0.0000

Data Index: 1718073 (The Pile)

Max Activating Token Index: 145

Text #5

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.5966. Min Act: -0.0000

Data Index: 1253960 (The Pile)

Max Activating Token Index: 511

Text #6

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.5711. Min Act: -0.0000

Data Index: 15661 (The Pile)

Max Activating Token Index: 653

Text #7

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.5645. Min Act: -0.0000

Data Index: 192686 (The Pile)

Max Activating Token Index: 87

Text #8

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.5847. Min Act: -0.0000

Data Index: 405048 (The Pile)

Max Activating Token Index: 116

Text #9

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.5752. Min Act: -0.0000

Data Index: 404849 (The Pile)

Max Activating Token Index: 509

Text #10

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.5693. Min Act: -0.0000

Data Index: 29301 (The Pile)

Max Activating Token Index: 190

Text #11

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.5496. Min Act: -0.0000

Data Index: 1149840 (The Pile)

Max Activating Token Index: 624

Text #12

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.5471. Min Act: -0.0000

Data Index: 1701397 (The Pile)

Max Activating Token Index: 616

Text #13

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.5566. Min Act: -0.0000

Data Index: 164361 (The Pile)

Max Activating Token Index: 101

Text #14

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.5536. Min Act: -0.0000

Data Index: 698163 (The Pile)

Max Activating Token Index: 364

Text #15

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.5389. Min Act: -0.0000

Data Index: 287854 (The Pile)

Max Activating Token Index: 240

Text #16

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.4835. Min Act: -0.0000

Data Index: 556670 (The Pile)

Max Activating Token Index: 762

Text #17

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.5494. Min Act: -0.0000

Data Index: 1217331 (The Pile)

Max Activating Token Index: 163

Text #18

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.5287. Min Act: -0.0000

Data Index: 1984807 (The Pile)

Max Activating Token Index: 461

Text #19

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.5480. Min Act: -0.0000

Data Index: 889992 (The Pile)

Max Activating Token Index: 181