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

Dataset: The Pile

Neuron 944 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: 0.4285. Min Range: -0.4285

Max Act: 0.4285. Min Act: -0.0000

Data Index: 1629742 (The Pile)

Max Activating Token Index: 989

Text #1

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.3635. Min Act: -0.0000

Data Index: 1788870 (The Pile)

Max Activating Token Index: 907

Text #2

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.3493. Min Act: -0.0000

Data Index: 398068 (The Pile)

Max Activating Token Index: 375

Text #3

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.3406. Min Act: -0.0000

Data Index: 359185 (The Pile)

Max Activating Token Index: 145

Text #4

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.3069. Min Act: -0.0000

Data Index: 1253403 (The Pile)

Max Activating Token Index: 707

Text #5

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.3034. Min Act: -0.0000

Data Index: 389192 (The Pile)

Max Activating Token Index: 569

Text #6

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.3184. Min Act: -0.0000

Data Index: 761283 (The Pile)

Max Activating Token Index: 247

Text #7

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.2970. Min Act: -0.0000

Data Index: 1974740 (The Pile)

Max Activating Token Index: 728

Text #8

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.3243. Min Act: -0.0000

Data Index: 1335607 (The Pile)

Max Activating Token Index: 622

Text #9

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.2897. Min Act: -0.0000

Data Index: 646227 (The Pile)

Max Activating Token Index: 663

Text #10

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.3151. Min Act: -0.0000

Data Index: 507348 (The Pile)

Max Activating Token Index: 420

Text #11

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.2676. Min Act: -0.0000

Data Index: 1392599 (The Pile)

Max Activating Token Index: 717

Text #12

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.3191. Min Act: -0.0000

Data Index: 227006 (The Pile)

Max Activating Token Index: 111

Text #13

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.2890. Min Act: -0.0000

Data Index: 825970 (The Pile)

Max Activating Token Index: 738

Text #14

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.3095. Min Act: -0.0000

Data Index: 1625146 (The Pile)

Max Activating Token Index: 647

Text #15

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.2914. Min Act: -0.0000

Data Index: 1639680 (The Pile)

Max Activating Token Index: 474

Text #16

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.3145. Min Act: -0.0000

Data Index: 302223 (The Pile)

Max Activating Token Index: 987

Text #17

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.2536. Min Act: -0.0000

Data Index: 508941 (The Pile)

Max Activating Token Index: 697

Text #18

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.3036. Min Act: -0.0000

Data Index: 1852669 (The Pile)

Max Activating Token Index: 212

Text #19

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.2937. Min Act: -0.0000

Data Index: 57332 (The Pile)

Max Activating Token Index: 803