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

Dataset: The Pile

Neuron 1635 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.3329. Min Act: -0.0000

Data Index: 1878024 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2884. Min Act: -0.0000

Data Index: 1561293 (The Pile)

Max Activating Token Index: 582

Text #2

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2752. Min Act: -0.0000

Data Index: 619386 (The Pile)

Max Activating Token Index: 854

Text #3

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2726. Min Act: -0.0000

Data Index: 331717 (The Pile)

Max Activating Token Index: 292

Text #4

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.3002. Min Act: -0.0000

Data Index: 659848 (The Pile)

Max Activating Token Index: 370

Text #5

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2929. Min Act: -0.0000

Data Index: 430553 (The Pile)

Max Activating Token Index: 526

Text #6

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2411. Min Act: -0.0000

Data Index: 176034 (The Pile)

Max Activating Token Index: 1001

Text #7

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2817. Min Act: -0.0000

Data Index: 806697 (The Pile)

Max Activating Token Index: 935

Text #8

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2461. Min Act: -0.0000

Data Index: 1832415 (The Pile)

Max Activating Token Index: 887

Text #9

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2405. Min Act: -0.0000

Data Index: 753152 (The Pile)

Max Activating Token Index: 936

Text #10

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2383. Min Act: -0.0000

Data Index: 1124785 (The Pile)

Max Activating Token Index: 890

Text #11

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2295. Min Act: -0.0000

Data Index: 845053 (The Pile)

Max Activating Token Index: 617

Text #12

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2162. Min Act: -0.0000

Data Index: 96168 (The Pile)

Max Activating Token Index: 869

Text #13

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2380. Min Act: -0.0000

Data Index: 1076307 (The Pile)

Max Activating Token Index: 888

Text #14

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2435. Min Act: -0.0000

Data Index: 487990 (The Pile)

Max Activating Token Index: 187

Text #15

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2456. Min Act: -0.0000

Data Index: 1970855 (The Pile)

Max Activating Token Index: 77

Text #16

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2379. Min Act: -0.0000

Data Index: 1491273 (The Pile)

Max Activating Token Index: 548

Text #17

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2668. Min Act: -0.0000

Data Index: 480652 (The Pile)

Max Activating Token Index: 597

Text #18

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2093. Min Act: -0.0000

Data Index: 737804 (The Pile)

Max Activating Token Index: 148

Text #19

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2232. Min Act: -0.0000

Data Index: 1030339 (The Pile)

Max Activating Token Index: 561