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

Dataset: The Pile

Neuron 2619 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: 0.3655. Min Range: -0.3655

Max Act: 0.3488. Min Act: -0.0000

Data Index: 1774109 (The Pile)

Max Activating Token Index: 108

Text #1

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.3351. Min Act: -0.0000

Data Index: 425391 (The Pile)

Max Activating Token Index: 361

Text #2

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.3368. Min Act: -0.0000

Data Index: 1407702 (The Pile)

Max Activating Token Index: 602

Text #3

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.3303. Min Act: -0.0000

Data Index: 450092 (The Pile)

Max Activating Token Index: 317

Text #4

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.3655. Min Act: -0.0000

Data Index: 832569 (The Pile)

Max Activating Token Index: 703

Text #5

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.3171. Min Act: -0.0000

Data Index: 61312 (The Pile)

Max Activating Token Index: 772

Text #6

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.3312. Min Act: -0.0000

Data Index: 951505 (The Pile)

Max Activating Token Index: 326

Text #7

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.3446. Min Act: -0.0000

Data Index: 1585811 (The Pile)

Max Activating Token Index: 580

Text #8

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.3078. Min Act: -0.0000

Data Index: 438212 (The Pile)

Max Activating Token Index: 505

Text #9

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.3056. Min Act: -0.0000

Data Index: 725712 (The Pile)

Max Activating Token Index: 855

Text #10

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.3104. Min Act: -0.0000

Data Index: 440946 (The Pile)

Max Activating Token Index: 327

Text #11

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.3084. Min Act: -0.0000

Data Index: 186024 (The Pile)

Max Activating Token Index: 816

Text #12

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.3055. Min Act: -0.0000

Data Index: 1590496 (The Pile)

Max Activating Token Index: 601

Text #13

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.2933. Min Act: -0.0000

Data Index: 80088 (The Pile)

Max Activating Token Index: 34

Text #14

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.3035. Min Act: -0.0000

Data Index: 1313546 (The Pile)

Max Activating Token Index: 181

Text #15

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.2750. Min Act: -0.0000

Data Index: 199229 (The Pile)

Max Activating Token Index: 389

Text #16

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.3226. Min Act: -0.0000

Data Index: 1653489 (The Pile)

Max Activating Token Index: 899

Text #17

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.2886. Min Act: -0.0000

Data Index: 882756 (The Pile)

Max Activating Token Index: 270

Text #18

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.2731. Min Act: -0.0000

Data Index: 1980359 (The Pile)

Max Activating Token Index: 600

Text #19

Max Range: 0.3655. Min Range: -0.3655

Max Act: 0.2929. Min Act: -0.0000

Data Index: 928650 (The Pile)

Max Activating Token Index: 196