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

Dataset: The Pile

Neuron 2448 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1959. Min Range: -1.1959

Max Act: 1.1959. Min Act: -0.0000

Data Index: 1795813 (The Pile)

Max Activating Token Index: 219

Text #1

Max Range: 1.1959. Min Range: -1.1959

Max Act: 1.1915. Min Act: -0.0000

Data Index: 221073 (The Pile)

Max Activating Token Index: 624

Text #2

Max Range: 1.1959. Min Range: -1.1959

Max Act: 0.9982. Min Act: -0.0000

Data Index: 904265 (The Pile)

Max Activating Token Index: 534

Text #3

Max Range: 1.1959. Min Range: -1.1959

Max Act: 1.1331. Min Act: -0.0000

Data Index: 1560824 (The Pile)

Max Activating Token Index: 374

Text #4

Max Range: 1.1959. Min Range: -1.1959

Max Act: 1.0029. Min Act: -0.0000

Data Index: 135490 (The Pile)

Max Activating Token Index: 380

Text #5

Max Range: 1.1959. Min Range: -1.1959

Max Act: 1.0530. Min Act: -0.0000

Data Index: 961526 (The Pile)

Max Activating Token Index: 280

Text #6

Max Range: 1.1959. Min Range: -1.1959

Max Act: 0.9662. Min Act: -0.0000

Data Index: 1787502 (The Pile)

Max Activating Token Index: 916

Text #7

Max Range: 1.1959. Min Range: -1.1959

Max Act: 0.9007. Min Act: -0.0000

Data Index: 1783594 (The Pile)

Max Activating Token Index: 441

Text #8

Max Range: 1.1959. Min Range: -1.1959

Max Act: 0.9302. Min Act: -0.0000

Data Index: 76602 (The Pile)

Max Activating Token Index: 911

Text #9

Max Range: 1.1959. Min Range: -1.1959

Max Act: 0.8935. Min Act: -0.0000

Data Index: 1565682 (The Pile)

Max Activating Token Index: 890

Text #10

Max Range: 1.1959. Min Range: -1.1959

Max Act: 0.9363. Min Act: -0.0000

Data Index: 830626 (The Pile)

Max Activating Token Index: 294

Text #11

Max Range: 1.1959. Min Range: -1.1959

Max Act: 0.8635. Min Act: -0.0000

Data Index: 372482 (The Pile)

Max Activating Token Index: 262

Text #12

Max Range: 1.1959. Min Range: -1.1959

Max Act: 0.8497. Min Act: -0.0000

Data Index: 944539 (The Pile)

Max Activating Token Index: 401

Text #13

Max Range: 1.1959. Min Range: -1.1959

Max Act: 0.8989. Min Act: -0.0000

Data Index: 1303738 (The Pile)

Max Activating Token Index: 270

Text #14

Max Range: 1.1959. Min Range: -1.1959

Max Act: 0.7890. Min Act: -0.0000

Data Index: 1978311 (The Pile)

Max Activating Token Index: 600

Text #15

Max Range: 1.1959. Min Range: -1.1959

Max Act: 0.7922. Min Act: -0.0000

Data Index: 207980 (The Pile)

Max Activating Token Index: 795

Text #16

Max Range: 1.1959. Min Range: -1.1959

Max Act: 0.7764. Min Act: -0.0000

Data Index: 348529 (The Pile)

Max Activating Token Index: 834

Text #17

Max Range: 1.1959. Min Range: -1.1959

Max Act: 0.8576. Min Act: -0.0000

Data Index: 1750533 (The Pile)

Max Activating Token Index: 795

Text #18

Max Range: 1.1959. Min Range: -1.1959

Max Act: 0.7850. Min Act: -0.0000

Data Index: 178435 (The Pile)

Max Activating Token Index: 207

Text #19

Max Range: 1.1959. Min Range: -1.1959

Max Act: 0.7127. Min Act: -0.0000

Data Index: 1759953 (The Pile)

Max Activating Token Index: 299