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

Dataset: The Pile

Neuron 456 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6332. Min Range: -3.6332

Max Act: 3.6332. Min Act: -0.0001

Data Index: 1385221 (The Pile)

Max Activating Token Index: 649

Text #1

Max Range: 3.6332. Min Range: -3.6332

Max Act: 3.5528. Min Act: -0.0000

Data Index: 590627 (The Pile)

Max Activating Token Index: 810

Text #2

Max Range: 3.6332. Min Range: -3.6332

Max Act: 3.3645. Min Act: -0.0000

Data Index: 1788754 (The Pile)

Max Activating Token Index: 411

Text #3

Max Range: 3.6332. Min Range: -3.6332

Max Act: 3.5659. Min Act: -0.0000

Data Index: 1262490 (The Pile)

Max Activating Token Index: 151

Text #4

Max Range: 3.6332. Min Range: -3.6332

Max Act: 3.2807. Min Act: -0.0000

Data Index: 1005717 (The Pile)

Max Activating Token Index: 470

Text #5

Max Range: 3.6332. Min Range: -3.6332

Max Act: 3.4558. Min Act: -0.0000

Data Index: 107809 (The Pile)

Max Activating Token Index: 395

Text #6

Max Range: 3.6332. Min Range: -3.6332

Max Act: 3.1359. Min Act: -0.0000

Data Index: 18494 (The Pile)

Max Activating Token Index: 204

Text #7

Max Range: 3.6332. Min Range: -3.6332

Max Act: 3.0454. Min Act: -0.0000

Data Index: 1221994 (The Pile)

Max Activating Token Index: 946

Text #8

Max Range: 3.6332. Min Range: -3.6332

Max Act: 2.7742. Min Act: -0.0000

Data Index: 971198 (The Pile)

Max Activating Token Index: 124

Text #9

Max Range: 3.6332. Min Range: -3.6332

Max Act: 2.8699. Min Act: -0.0000

Data Index: 221460 (The Pile)

Max Activating Token Index: 315

Text #10

Max Range: 3.6332. Min Range: -3.6332

Max Act: 2.6873. Min Act: -0.0000

Data Index: 1014810 (The Pile)

Max Activating Token Index: 148

Text #11

Max Range: 3.6332. Min Range: -3.6332

Max Act: 2.7439. Min Act: -0.0000

Data Index: 1605010 (The Pile)

Max Activating Token Index: 791

Text #12

Max Range: 3.6332. Min Range: -3.6332

Max Act: 1.9041. Min Act: -0.0000

Data Index: 613581 (The Pile)

Max Activating Token Index: 1004

Text #13

Max Range: 3.6332. Min Range: -3.6332

Max Act: 2.0549. Min Act: -0.0000

Data Index: 614961 (The Pile)

Max Activating Token Index: 974

Text #14

Max Range: 3.6332. Min Range: -3.6332

Max Act: 1.9520. Min Act: -0.0000

Data Index: 1923937 (The Pile)

Max Activating Token Index: 214

Text #15

Max Range: 3.6332. Min Range: -3.6332

Max Act: 1.7526. Min Act: -0.0000

Data Index: 1689883 (The Pile)

Max Activating Token Index: 846

Text #16

Max Range: 3.6332. Min Range: -3.6332

Max Act: 1.6153. Min Act: -0.0000

Data Index: 1588425 (The Pile)

Max Activating Token Index: 270

Text #17

Max Range: 3.6332. Min Range: -3.6332

Max Act: 1.5320. Min Act: -0.0000

Data Index: 1035772 (The Pile)

Max Activating Token Index: 495

Text #18

Max Range: 3.6332. Min Range: -3.6332

Max Act: 1.7704. Min Act: -0.0000

Data Index: 1346729 (The Pile)

Max Activating Token Index: 1015

Text #19

Max Range: 3.6332. Min Range: -3.6332

Max Act: 1.6264. Min Act: -0.0000

Data Index: 1502754 (The Pile)

Max Activating Token Index: 832