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

Dataset: The Pile

Neuron 694 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: 0.3999. Min Range: -0.3999

Max Act: 0.3999. Min Act: -0.0000

Data Index: 1142228 (The Pile)

Max Activating Token Index: 657

Text #1

Max Range: 0.3999. Min Range: -0.3999

Max Act: 0.3981. Min Act: -0.0000

Data Index: 1746200 (The Pile)

Max Activating Token Index: 211

Text #2

Max Range: 0.3999. Min Range: -0.3999

Max Act: 0.3826. Min Act: -0.0000

Data Index: 1261223 (The Pile)

Max Activating Token Index: 264

Text #3

Max Range: 0.3999. Min Range: -0.3999

Max Act: 0.3957. Min Act: -0.0000

Data Index: 1236797 (The Pile)

Max Activating Token Index: 66

Text #4

Max Range: 0.3999. Min Range: -0.3999

Max Act: 0.3682. Min Act: -0.0000

Data Index: 1062227 (The Pile)

Max Activating Token Index: 208

Text #5

Max Range: 0.3999. Min Range: -0.3999

Max Act: 0.3562. Min Act: -0.0000

Data Index: 1062558 (The Pile)

Max Activating Token Index: 815

Text #6

Max Range: 0.3999. Min Range: -0.3999

Max Act: 0.3570. Min Act: -0.0000

Data Index: 903420 (The Pile)

Max Activating Token Index: 416

Text #7

Max Range: 0.3999. Min Range: -0.3999

Max Act: 0.3620. Min Act: -0.0000

Data Index: 342085 (The Pile)

Max Activating Token Index: 319

Text #8

Max Range: 0.3999. Min Range: -0.3999

Max Act: 0.3595. Min Act: -0.0000

Data Index: 1357713 (The Pile)

Max Activating Token Index: 370

Text #9

Max Range: 0.3999. Min Range: -0.3999

Max Act: 0.3471. Min Act: -0.0000

Data Index: 190704 (The Pile)

Max Activating Token Index: 54

Text #10

Max Range: 0.3999. Min Range: -0.3999

Max Act: 0.3642. Min Act: -0.0000

Data Index: 347407 (The Pile)

Max Activating Token Index: 985

Text #11

Max Range: 0.3999. Min Range: -0.3999

Max Act: 0.3400. Min Act: -0.0000

Data Index: 1603764 (The Pile)

Max Activating Token Index: 676

Text #12

Max Range: 0.3999. Min Range: -0.3999

Max Act: 0.3431. Min Act: -0.0000

Data Index: 278999 (The Pile)

Max Activating Token Index: 586

Text #13

Max Range: 0.3999. Min Range: -0.3999

Max Act: 0.3380. Min Act: -0.0000

Data Index: 1123901 (The Pile)

Max Activating Token Index: 537

Text #14

Max Range: 0.3999. Min Range: -0.3999

Max Act: 0.3405. Min Act: -0.0000

Data Index: 1294482 (The Pile)

Max Activating Token Index: 564

Text #15

Max Range: 0.3999. Min Range: -0.3999

Max Act: 0.2997. Min Act: -0.0000

Data Index: 951238 (The Pile)

Max Activating Token Index: 752

Text #16

Max Range: 0.3999. Min Range: -0.3999

Max Act: 0.3146. Min Act: -0.0000

Data Index: 303107 (The Pile)

Max Activating Token Index: 51

Text #17

Max Range: 0.3999. Min Range: -0.3999

Max Act: 0.2906. Min Act: -0.0000

Data Index: 1662611 (The Pile)

Max Activating Token Index: 921

Text #18

Max Range: 0.3999. Min Range: -0.3999

Max Act: 0.3194. Min Act: -0.0000

Data Index: 1393989 (The Pile)

Max Activating Token Index: 484

Text #19

Max Range: 0.3999. Min Range: -0.3999

Max Act: 0.3103. Min Act: -0.0000

Data Index: 1450203 (The Pile)

Max Activating Token Index: 921