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

Dataset: The Pile

Neuron 488 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.9158. Min Act: -0.0000

Data Index: 1590718 (The Pile)

Max Activating Token Index: 396

Text #1

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.9064. Min Act: -0.0000

Data Index: 246377 (The Pile)

Max Activating Token Index: 465

Text #2

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.8575. Min Act: -0.0000

Data Index: 761624 (The Pile)

Max Activating Token Index: 555

Text #3

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.7604. Min Act: -0.0000

Data Index: 1340284 (The Pile)

Max Activating Token Index: 845

Text #4

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.8421. Min Act: -0.0000

Data Index: 1747053 (The Pile)

Max Activating Token Index: 437

Text #5

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.7545. Min Act: -0.0000

Data Index: 1113272 (The Pile)

Max Activating Token Index: 829

Text #6

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.7687. Min Act: -0.0000

Data Index: 1889639 (The Pile)

Max Activating Token Index: 300

Text #7

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.7701. Min Act: -0.0000

Data Index: 1410286 (The Pile)

Max Activating Token Index: 283

Text #8

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.8080. Min Act: -0.0000

Data Index: 1900224 (The Pile)

Max Activating Token Index: 541

Text #9

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.8628. Min Act: -0.0000

Data Index: 370633 (The Pile)

Max Activating Token Index: 752

Text #10

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.7508. Min Act: -0.0000

Data Index: 1763086 (The Pile)

Max Activating Token Index: 89

Text #11

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.7734. Min Act: -0.0000

Data Index: 1208134 (The Pile)

Max Activating Token Index: 676

Text #12

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.6782. Min Act: -0.0000

Data Index: 1134774 (The Pile)

Max Activating Token Index: 411

Text #13

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.6915. Min Act: -0.0000

Data Index: 1194448 (The Pile)

Max Activating Token Index: 689

Text #14

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.7450. Min Act: -0.0000

Data Index: 1402410 (The Pile)

Max Activating Token Index: 357

Text #15

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.7515. Min Act: -0.0000

Data Index: 323129 (The Pile)

Max Activating Token Index: 611

Text #16

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.7219. Min Act: -0.0000

Data Index: 1425795 (The Pile)

Max Activating Token Index: 676

Text #17

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.7046. Min Act: -0.0000

Data Index: 1492079 (The Pile)

Max Activating Token Index: 97

Text #18

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.7489. Min Act: -0.0000

Data Index: 1452016 (The Pile)

Max Activating Token Index: 225

Text #19

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.7314. Min Act: -0.0000

Data Index: 1594577 (The Pile)

Max Activating Token Index: 281