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

Dataset: The Pile

Neuron 330 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0756. Min Range: -1.0756

Max Act: 1.0756. Min Act: -0.0000

Data Index: 1551306 (The Pile)

Max Activating Token Index: 70

Text #1

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.9224. Min Act: -0.0000

Data Index: 1958567 (The Pile)

Max Activating Token Index: 61

Text #2

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.7824. Min Act: -0.0000

Data Index: 273315 (The Pile)

Max Activating Token Index: 694

Text #3

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.6523. Min Act: -0.0000

Data Index: 1889506 (The Pile)

Max Activating Token Index: 404

Text #4

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.6953. Min Act: -0.0000

Data Index: 203286 (The Pile)

Max Activating Token Index: 610

Text #5

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.6529. Min Act: -0.0000

Data Index: 394284 (The Pile)

Max Activating Token Index: 78

Text #6

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.6590. Min Act: -0.0000

Data Index: 1980142 (The Pile)

Max Activating Token Index: 394

Text #7

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.5625. Min Act: -0.0000

Data Index: 1199600 (The Pile)

Max Activating Token Index: 787

Text #8

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.5585. Min Act: -0.0000

Data Index: 175485 (The Pile)

Max Activating Token Index: 365

Text #9

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.6404. Min Act: -0.0000

Data Index: 1001785 (The Pile)

Max Activating Token Index: 694

Text #10

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.5202. Min Act: -0.0000

Data Index: 1943515 (The Pile)

Max Activating Token Index: 608

Text #11

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.5246. Min Act: -0.0000

Data Index: 1969280 (The Pile)

Max Activating Token Index: 9

Text #12

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.5565. Min Act: -0.0000

Data Index: 1672499 (The Pile)

Max Activating Token Index: 39

Text #13

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.5416. Min Act: -0.0000

Data Index: 456345 (The Pile)

Max Activating Token Index: 14

Text #14

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.4946. Min Act: -0.0000

Data Index: 1825526 (The Pile)

Max Activating Token Index: 568

Text #15

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.5130. Min Act: -0.0000

Data Index: 1734927 (The Pile)

Max Activating Token Index: 12

Text #16

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.5142. Min Act: -0.0000

Data Index: 1525288 (The Pile)

Max Activating Token Index: 16

Text #17

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.5036. Min Act: -0.0000

Data Index: 1921592 (The Pile)

Max Activating Token Index: 716

Text #18

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.5194. Min Act: -0.0000

Data Index: 1702180 (The Pile)

Max Activating Token Index: 528

Text #19

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.4735. Min Act: -0.0000

Data Index: 974108 (The Pile)

Max Activating Token Index: 626