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

Dataset: The Pile

Neuron 3862 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9489. Min Range: -3.9489

Max Act: 3.9489. Min Act: -0.0000

Data Index: 149003 (The Pile)

Max Activating Token Index: 916

Text #1

Max Range: 3.9489. Min Range: -3.9489

Max Act: 3.5652. Min Act: -0.0000

Data Index: 283383 (The Pile)

Max Activating Token Index: 363

Text #2

Max Range: 3.9489. Min Range: -3.9489

Max Act: 3.5072. Min Act: -0.0000

Data Index: 1234811 (The Pile)

Max Activating Token Index: 252

Text #3

Max Range: 3.9489. Min Range: -3.9489

Max Act: 3.2957. Min Act: -0.0000

Data Index: 1824283 (The Pile)

Max Activating Token Index: 856

Text #4

Max Range: 3.9489. Min Range: -3.9489

Max Act: 3.4178. Min Act: -0.0000

Data Index: 1057314 (The Pile)

Max Activating Token Index: 902

Text #5

Max Range: 3.9489. Min Range: -3.9489

Max Act: 3.3519. Min Act: -0.0000

Data Index: 1423694 (The Pile)

Max Activating Token Index: 457

Text #6

Max Range: 3.9489. Min Range: -3.9489

Max Act: 3.5561. Min Act: -0.0000

Data Index: 1847144 (The Pile)

Max Activating Token Index: 740

Text #7

Max Range: 3.9489. Min Range: -3.9489

Max Act: 3.0688. Min Act: -0.0000

Data Index: 1562458 (The Pile)

Max Activating Token Index: 58

Text #8

Max Range: 3.9489. Min Range: -3.9489

Max Act: 3.2114. Min Act: -0.0000

Data Index: 1911876 (The Pile)

Max Activating Token Index: 339

Text #9

Max Range: 3.9489. Min Range: -3.9489

Max Act: 3.4580. Min Act: -0.0000

Data Index: 1018996 (The Pile)

Max Activating Token Index: 687

Text #10

Max Range: 3.9489. Min Range: -3.9489

Max Act: 2.7818. Min Act: -0.0000

Data Index: 113513 (The Pile)

Max Activating Token Index: 73

Text #11

Max Range: 3.9489. Min Range: -3.9489

Max Act: 2.9425. Min Act: -0.0000

Data Index: 958497 (The Pile)

Max Activating Token Index: 156

Text #12

Max Range: 3.9489. Min Range: -3.9489

Max Act: 2.9587. Min Act: -0.0000

Data Index: 348387 (The Pile)

Max Activating Token Index: 73

Text #13

Max Range: 3.9489. Min Range: -3.9489

Max Act: 2.6595. Min Act: -0.0000

Data Index: 1492394 (The Pile)

Max Activating Token Index: 418

Text #14

Max Range: 3.9489. Min Range: -3.9489

Max Act: 2.6556. Min Act: -0.0000

Data Index: 250299 (The Pile)

Max Activating Token Index: 755

Text #15

Max Range: 3.9489. Min Range: -3.9489

Max Act: 2.9005. Min Act: -0.0000

Data Index: 638151 (The Pile)

Max Activating Token Index: 415

Text #16

Max Range: 3.9489. Min Range: -3.9489

Max Act: 2.7615. Min Act: -0.0000

Data Index: 1948576 (The Pile)

Max Activating Token Index: 431

Text #17

Max Range: 3.9489. Min Range: -3.9489

Max Act: 2.7225. Min Act: -0.0000

Data Index: 341886 (The Pile)

Max Activating Token Index: 94

Text #18

Max Range: 3.9489. Min Range: -3.9489

Max Act: 2.8722. Min Act: -0.0000

Data Index: 1591466 (The Pile)

Max Activating Token Index: 526

Text #19

Max Range: 3.9489. Min Range: -3.9489

Max Act: 2.7156. Min Act: -0.0000

Data Index: 1026853 (The Pile)

Max Activating Token Index: 463