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

Dataset: The Pile

Neuron 2407 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: 1.0570. Min Range: -1.0570

Max Act: 0.9966. Min Act: -0.0000

Data Index: 602276 (The Pile)

Max Activating Token Index: 316

Text #1

Max Range: 1.0570. Min Range: -1.0570

Max Act: 1.0570. Min Act: -0.0000

Data Index: 1871034 (The Pile)

Max Activating Token Index: 975

Text #2

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.9691. Min Act: -0.0000

Data Index: 1534413 (The Pile)

Max Activating Token Index: 456

Text #3

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.8172. Min Act: 0.0000

Data Index: 890962 (The Pile)

Max Activating Token Index: 455

Text #4

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.7803. Min Act: -0.0000

Data Index: 892852 (The Pile)

Max Activating Token Index: 378

Text #5

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.7696. Min Act: -0.0000

Data Index: 820825 (The Pile)

Max Activating Token Index: 90

Text #6

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.7917. Min Act: -0.0000

Data Index: 1322247 (The Pile)

Max Activating Token Index: 984

Text #7

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.7092. Min Act: -0.0000

Data Index: 18143 (The Pile)

Max Activating Token Index: 135

Text #8

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.7002. Min Act: 0.0000

Data Index: 421026 (The Pile)

Max Activating Token Index: 452

Text #9

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.7295. Min Act: -0.0000

Data Index: 1728609 (The Pile)

Max Activating Token Index: 1004

Text #10

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.7034. Min Act: -0.0000

Data Index: 259757 (The Pile)

Max Activating Token Index: 150

Text #11

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.6622. Min Act: 0.0000

Data Index: 1272821 (The Pile)

Max Activating Token Index: 539

Text #12

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.6671. Min Act: -0.0000

Data Index: 148929 (The Pile)

Max Activating Token Index: 539

Text #13

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.6589. Min Act: -0.0000

Data Index: 33338 (The Pile)

Max Activating Token Index: 618

Text #14

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.6459. Min Act: -0.0000

Data Index: 268237 (The Pile)

Max Activating Token Index: 521

Text #15

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.6071. Min Act: -0.0000

Data Index: 1838379 (The Pile)

Max Activating Token Index: 316

Text #16

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.6245. Min Act: 0.0000

Data Index: 1078412 (The Pile)

Max Activating Token Index: 297

Text #17

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.5711. Min Act: 0.0000

Data Index: 221907 (The Pile)

Max Activating Token Index: 832

Text #18

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.6177. Min Act: 0.0000

Data Index: 1786578 (The Pile)

Max Activating Token Index: 398

Text #19

Max Range: 1.0570. Min Range: -1.0570

Max Act: 0.5947. Min Act: -0.0000

Data Index: 1162435 (The Pile)

Max Activating Token Index: 983