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

Dataset: The Pile

Neuron 3036 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2660. Min Range: -1.2660

Max Act: 1.2660. Min Act: -0.0000

Data Index: 519957 (The Pile)

Max Activating Token Index: 484

Text #1

Max Range: 1.2660. Min Range: -1.2660

Max Act: 1.0620. Min Act: -0.0000

Data Index: 492364 (The Pile)

Max Activating Token Index: 337

Text #2

Max Range: 1.2660. Min Range: -1.2660

Max Act: 1.1343. Min Act: -0.0000

Data Index: 1350418 (The Pile)

Max Activating Token Index: 539

Text #3

Max Range: 1.2660. Min Range: -1.2660

Max Act: 1.0373. Min Act: -0.0000

Data Index: 229467 (The Pile)

Max Activating Token Index: 291

Text #4

Max Range: 1.2660. Min Range: -1.2660

Max Act: 1.1392. Min Act: -0.0000

Data Index: 578659 (The Pile)

Max Activating Token Index: 192

Text #5

Max Range: 1.2660. Min Range: -1.2660

Max Act: 1.0489. Min Act: -0.0000

Data Index: 791295 (The Pile)

Max Activating Token Index: 140

Text #6

Max Range: 1.2660. Min Range: -1.2660

Max Act: 1.0298. Min Act: -0.0000

Data Index: 1689650 (The Pile)

Max Activating Token Index: 63

Text #7

Max Range: 1.2660. Min Range: -1.2660

Max Act: 0.9873. Min Act: -0.0000

Data Index: 930858 (The Pile)

Max Activating Token Index: 214

Text #8

Max Range: 1.2660. Min Range: -1.2660

Max Act: 1.0914. Min Act: -0.0000

Data Index: 342586 (The Pile)

Max Activating Token Index: 394

Text #9

Max Range: 1.2660. Min Range: -1.2660

Max Act: 1.0786. Min Act: -0.0000

Data Index: 1672894 (The Pile)

Max Activating Token Index: 175

Text #10

Max Range: 1.2660. Min Range: -1.2660

Max Act: 1.0170. Min Act: -0.0000

Data Index: 1833799 (The Pile)

Max Activating Token Index: 162

Text #11

Max Range: 1.2660. Min Range: -1.2660

Max Act: 1.0120. Min Act: -0.0000

Data Index: 896817 (The Pile)

Max Activating Token Index: 100

Text #12

Max Range: 1.2660. Min Range: -1.2660

Max Act: 1.0038. Min Act: -0.0000

Data Index: 599630 (The Pile)

Max Activating Token Index: 526

Text #13

Max Range: 1.2660. Min Range: -1.2660

Max Act: 0.9946. Min Act: -0.0000

Data Index: 700435 (The Pile)

Max Activating Token Index: 133

Text #14

Max Range: 1.2660. Min Range: -1.2660

Max Act: 0.9850. Min Act: -0.0000

Data Index: 1689586 (The Pile)

Max Activating Token Index: 840

Text #15

Max Range: 1.2660. Min Range: -1.2660

Max Act: 0.9839. Min Act: -0.0000

Data Index: 420208 (The Pile)

Max Activating Token Index: 290

Text #16

Max Range: 1.2660. Min Range: -1.2660

Max Act: 0.9255. Min Act: -0.0000

Data Index: 1030662 (The Pile)

Max Activating Token Index: 657

Text #17

Max Range: 1.2660. Min Range: -1.2660

Max Act: 0.9305. Min Act: -0.0000

Data Index: 88478 (The Pile)

Max Activating Token Index: 315

Text #18

Max Range: 1.2660. Min Range: -1.2660

Max Act: 0.7498. Min Act: -0.0000

Data Index: 741105 (The Pile)

Max Activating Token Index: 806

Text #19

Max Range: 1.2660. Min Range: -1.2660

Max Act: 0.9691. Min Act: -0.0000

Data Index: 819192 (The Pile)

Max Activating Token Index: 694