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

Dataset: The Pile

Neuron 2804 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3567. Min Range: -5.3567

Max Act: 5.3567. Min Act: -0.0000

Data Index: 313772 (The Pile)

Max Activating Token Index: 451

Text #1

Max Range: 5.3567. Min Range: -5.3567

Max Act: 3.7586. Min Act: -0.0000

Data Index: 250764 (The Pile)

Max Activating Token Index: 190

Text #2

Max Range: 5.3567. Min Range: -5.3567

Max Act: 3.7273. Min Act: -0.0000

Data Index: 1098881 (The Pile)

Max Activating Token Index: 747

Text #3

Max Range: 5.3567. Min Range: -5.3567

Max Act: 3.8014. Min Act: -0.0000

Data Index: 904443 (The Pile)

Max Activating Token Index: 512

Text #4

Max Range: 5.3567. Min Range: -5.3567

Max Act: 3.4131. Min Act: -0.0000

Data Index: 1358030 (The Pile)

Max Activating Token Index: 119

Text #5

Max Range: 5.3567. Min Range: -5.3567

Max Act: 3.6776. Min Act: -0.0000

Data Index: 1370230 (The Pile)

Max Activating Token Index: 584

Text #6

Max Range: 5.3567. Min Range: -5.3567

Max Act: 3.7892. Min Act: -0.0000

Data Index: 485253 (The Pile)

Max Activating Token Index: 309

Text #7

Max Range: 5.3567. Min Range: -5.3567

Max Act: 3.1727. Min Act: -0.0000

Data Index: 1488192 (The Pile)

Max Activating Token Index: 131

Text #8

Max Range: 5.3567. Min Range: -5.3567

Max Act: 3.1346. Min Act: -0.0000

Data Index: 231329 (The Pile)

Max Activating Token Index: 640

Text #9

Max Range: 5.3567. Min Range: -5.3567

Max Act: 2.4115. Min Act: -0.0000

Data Index: 1555182 (The Pile)

Max Activating Token Index: 221

Text #10

Max Range: 5.3567. Min Range: -5.3567

Max Act: 2.6537. Min Act: -0.0000

Data Index: 518411 (The Pile)

Max Activating Token Index: 463

Text #11

Max Range: 5.3567. Min Range: -5.3567

Max Act: 2.4778. Min Act: -0.0000

Data Index: 361047 (The Pile)

Max Activating Token Index: 198

Text #12

Max Range: 5.3567. Min Range: -5.3567

Max Act: 2.4738. Min Act: -0.0000

Data Index: 1847872 (The Pile)

Max Activating Token Index: 132

Text #13

Max Range: 5.3567. Min Range: -5.3567

Max Act: 2.1100. Min Act: -0.0000

Data Index: 1149129 (The Pile)

Max Activating Token Index: 918

Text #14

Max Range: 5.3567. Min Range: -5.3567

Max Act: 2.7946. Min Act: -0.0000

Data Index: 1793289 (The Pile)

Max Activating Token Index: 222

Text #15

Max Range: 5.3567. Min Range: -5.3567

Max Act: 2.7026. Min Act: -0.0000

Data Index: 775900 (The Pile)

Max Activating Token Index: 318

Text #16

Max Range: 5.3567. Min Range: -5.3567

Max Act: 2.3819. Min Act: -0.0000

Data Index: 620039 (The Pile)

Max Activating Token Index: 223

Text #17

Max Range: 5.3567. Min Range: -5.3567

Max Act: 2.3342. Min Act: -0.0000

Data Index: 400088 (The Pile)

Max Activating Token Index: 489

Text #18

Max Range: 5.3567. Min Range: -5.3567

Max Act: 2.6310. Min Act: -0.0000

Data Index: 1510400 (The Pile)

Max Activating Token Index: 566

Text #19

Max Range: 5.3567. Min Range: -5.3567

Max Act: 2.4580. Min Act: -0.0000

Data Index: 862623 (The Pile)

Max Activating Token Index: 109