Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 432 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.5583. Min Range: -0.5583

Max Act: 0.5583. Min Act: -0.0001

Data Index: 945044 (The Pile)

Max Activating Token Index: 937

Text #1

Max Range: 0.5583. Min Range: -0.5583

Max Act: 0.5098. Min Act: -0.0000

Data Index: 1432548 (The Pile)

Max Activating Token Index: 277

Text #2

Max Range: 0.5583. Min Range: -0.5583

Max Act: 0.4474. Min Act: -0.0001

Data Index: 76110 (The Pile)

Max Activating Token Index: 872

Text #3

Max Range: 0.5583. Min Range: -0.5583

Max Act: 0.4526. Min Act: -0.0000

Data Index: 617906 (The Pile)

Max Activating Token Index: 956

Text #4

Max Range: 0.5583. Min Range: -0.5583

Max Act: 0.4513. Min Act: -0.0001

Data Index: 120403 (The Pile)

Max Activating Token Index: 155

Text #5

Max Range: 0.5583. Min Range: -0.5583

Max Act: 0.4246. Min Act: -0.0001

Data Index: 760465 (The Pile)

Max Activating Token Index: 427

Text #6

Max Range: 0.5583. Min Range: -0.5583

Max Act: 0.4343. Min Act: -0.0000

Data Index: 1759965 (The Pile)

Max Activating Token Index: 160

Text #7

Max Range: 0.5583. Min Range: -0.5583

Max Act: 0.4322. Min Act: -0.0000

Data Index: 580701 (The Pile)

Max Activating Token Index: 540

Text #8

Max Range: 0.5583. Min Range: -0.5583

Max Act: 0.4326. Min Act: -0.0000

Data Index: 1568224 (The Pile)

Max Activating Token Index: 408

Text #9

Max Range: 0.5583. Min Range: -0.5583

Max Act: 0.4286. Min Act: -0.0000

Data Index: 531193 (The Pile)

Max Activating Token Index: 995

Text #10

Max Range: 0.5583. Min Range: -0.5583

Max Act: 0.4209. Min Act: -0.0001

Data Index: 1595908 (The Pile)

Max Activating Token Index: 1016

Text #11

Max Range: 0.5583. Min Range: -0.5583

Max Act: 0.4085. Min Act: -0.0001

Data Index: 134677 (The Pile)

Max Activating Token Index: 737

Text #12

Max Range: 0.5583. Min Range: -0.5583

Max Act: 0.4207. Min Act: -0.0000

Data Index: 842262 (The Pile)

Max Activating Token Index: 151

Text #13

Max Range: 0.5583. Min Range: -0.5583

Max Act: 0.4076. Min Act: -0.0000

Data Index: 1692014 (The Pile)

Max Activating Token Index: 686

Text #14

Max Range: 0.5583. Min Range: -0.5583

Max Act: 0.4052. Min Act: -0.0000

Data Index: 1910168 (The Pile)

Max Activating Token Index: 92

Text #15

Max Range: 0.5583. Min Range: -0.5583

Max Act: 0.4046. Min Act: -0.0000

Data Index: 433072 (The Pile)

Max Activating Token Index: 55

Text #16

Max Range: 0.5583. Min Range: -0.5583

Max Act: 0.4019. Min Act: -0.0000

Data Index: 422064 (The Pile)

Max Activating Token Index: 640

Text #17

Max Range: 0.5583. Min Range: -0.5583

Max Act: 0.4104. Min Act: -0.0000

Data Index: 1079029 (The Pile)

Max Activating Token Index: 111

Text #18

Max Range: 0.5583. Min Range: -0.5583

Max Act: 0.4104. Min Act: -0.0001

Data Index: 193732 (The Pile)

Max Activating Token Index: 469

Text #19

Max Range: 0.5583. Min Range: -0.5583

Max Act: 0.4096. Min Act: -0.0000

Data Index: 123378 (The Pile)

Max Activating Token Index: 482