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

Dataset: The Pile

Neuron 4380 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: 0.8416. Min Range: -0.8416

Max Act: 0.8416. Min Act: -0.0000

Data Index: 1903076 (The Pile)

Max Activating Token Index: 429

Text #1

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.7593. Min Act: -0.0000

Data Index: 144227 (The Pile)

Max Activating Token Index: 81

Text #2

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.6547. Min Act: -0.0000

Data Index: 741534 (The Pile)

Max Activating Token Index: 391

Text #3

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.5606. Min Act: -0.0000

Data Index: 1244941 (The Pile)

Max Activating Token Index: 177

Text #4

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.6220. Min Act: -0.0000

Data Index: 1052804 (The Pile)

Max Activating Token Index: 667

Text #5

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.6300. Min Act: -0.0000

Data Index: 89466 (The Pile)

Max Activating Token Index: 144

Text #6

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.6206. Min Act: -0.0000

Data Index: 594374 (The Pile)

Max Activating Token Index: 419

Text #7

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.5952. Min Act: -0.0000

Data Index: 1398374 (The Pile)

Max Activating Token Index: 433

Text #8

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.6049. Min Act: -0.0000

Data Index: 763848 (The Pile)

Max Activating Token Index: 329

Text #9

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.5866. Min Act: -0.0000

Data Index: 1159103 (The Pile)

Max Activating Token Index: 240

Text #10

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.5438. Min Act: -0.0000

Data Index: 207677 (The Pile)

Max Activating Token Index: 146

Text #11

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.5511. Min Act: -0.0000

Data Index: 1769848 (The Pile)

Max Activating Token Index: 260

Text #12

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.5545. Min Act: -0.0000

Data Index: 1414618 (The Pile)

Max Activating Token Index: 998

Text #13

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.5303. Min Act: -0.0000

Data Index: 710344 (The Pile)

Max Activating Token Index: 117

Text #14

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.5339. Min Act: -0.0000

Data Index: 782027 (The Pile)

Max Activating Token Index: 262

Text #15

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.5303. Min Act: -0.0000

Data Index: 599475 (The Pile)

Max Activating Token Index: 461

Text #16

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.5337. Min Act: -0.0000

Data Index: 1322618 (The Pile)

Max Activating Token Index: 398

Text #17

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.5027. Min Act: -0.0000

Data Index: 269639 (The Pile)

Max Activating Token Index: 673

Text #18

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.4865. Min Act: -0.0000

Data Index: 1600233 (The Pile)

Max Activating Token Index: 578

Text #19

Max Range: 0.8416. Min Range: -0.8416

Max Act: 0.4698. Min Act: -0.0000

Data Index: 1296402 (The Pile)

Max Activating Token Index: 472