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

Dataset: The Pile

Neuron 1332 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 7.3909. Min Range: -7.3909

Max Act: 7.3331. Min Act: -0.0000

Data Index: 1840219 (The Pile)

Max Activating Token Index: 77

Text #1

Max Range: 7.3909. Min Range: -7.3909

Max Act: 7.3198. Min Act: -0.0000

Data Index: 1218958 (The Pile)

Max Activating Token Index: 245

Text #2

Max Range: 7.3909. Min Range: -7.3909

Max Act: 7.3151. Min Act: -0.0000

Data Index: 794107 (The Pile)

Max Activating Token Index: 267

Text #3

Max Range: 7.3909. Min Range: -7.3909

Max Act: 7.1207. Min Act: -0.0000

Data Index: 766170 (The Pile)

Max Activating Token Index: 141

Text #4

Max Range: 7.3909. Min Range: -7.3909

Max Act: 7.2169. Min Act: -0.0000

Data Index: 304101 (The Pile)

Max Activating Token Index: 115

Text #5

Max Range: 7.3909. Min Range: -7.3909

Max Act: 7.3909. Min Act: -0.0000

Data Index: 781016 (The Pile)

Max Activating Token Index: 135

Text #6

Max Range: 7.3909. Min Range: -7.3909

Max Act: 7.3742. Min Act: -0.0000

Data Index: 632699 (The Pile)

Max Activating Token Index: 202

Text #7

Max Range: 7.3909. Min Range: -7.3909

Max Act: 7.1264. Min Act: -0.0000

Data Index: 43629 (The Pile)

Max Activating Token Index: 13

Text #8

Max Range: 7.3909. Min Range: -7.3909

Max Act: 7.0946. Min Act: -0.0000

Data Index: 337182 (The Pile)

Max Activating Token Index: 291

Text #9

Max Range: 7.3909. Min Range: -7.3909

Max Act: 7.0688. Min Act: -0.0000

Data Index: 79039 (The Pile)

Max Activating Token Index: 32

Text #10

Max Range: 7.3909. Min Range: -7.3909

Max Act: 6.8559. Min Act: -0.0000

Data Index: 1757071 (The Pile)

Max Activating Token Index: 113

Text #11

Max Range: 7.3909. Min Range: -7.3909

Max Act: 6.9915. Min Act: -0.0000

Data Index: 1162631 (The Pile)

Max Activating Token Index: 20

Text #12

Max Range: 7.3909. Min Range: -7.3909

Max Act: 7.0079. Min Act: -0.0000

Data Index: 1889271 (The Pile)

Max Activating Token Index: 75

Text #13

Max Range: 7.3909. Min Range: -7.3909

Max Act: 6.7991. Min Act: -0.0000

Data Index: 249045 (The Pile)

Max Activating Token Index: 118

Text #14

Max Range: 7.3909. Min Range: -7.3909

Max Act: 6.9550. Min Act: -0.0000

Data Index: 1022560 (The Pile)

Max Activating Token Index: 38

Text #15

Max Range: 7.3909. Min Range: -7.3909

Max Act: 6.9452. Min Act: -0.0000

Data Index: 1066900 (The Pile)

Max Activating Token Index: 38

Text #16

Max Range: 7.3909. Min Range: -7.3909

Max Act: 7.0969. Min Act: -0.0000

Data Index: 1128 (The Pile)

Max Activating Token Index: 167

Text #17

Max Range: 7.3909. Min Range: -7.3909

Max Act: 7.1044. Min Act: -0.0000

Data Index: 1617765 (The Pile)

Max Activating Token Index: 220

Text #18

Max Range: 7.3909. Min Range: -7.3909

Max Act: 6.9023. Min Act: -0.0000

Data Index: 1512394 (The Pile)

Max Activating Token Index: 75

Text #19

Max Range: 7.3909. Min Range: -7.3909

Max Act: 6.8957. Min Act: -0.0000

Data Index: 76455 (The Pile)

Max Activating Token Index: 372