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

Dataset: The Pile

Neuron 4702 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.8153. Min Range: -7.8153

Max Act: 7.0811. Min Act: -0.0000

Data Index: 638647 (The Pile)

Max Activating Token Index: 785

Text #1

Max Range: 7.8153. Min Range: -7.8153

Max Act: 7.8153. Min Act: -0.0000

Data Index: 1544535 (The Pile)

Max Activating Token Index: 616

Text #2

Max Range: 7.8153. Min Range: -7.8153

Max Act: 7.2566. Min Act: -0.0000

Data Index: 923793 (The Pile)

Max Activating Token Index: 423

Text #3

Max Range: 7.8153. Min Range: -7.8153

Max Act: 7.3758. Min Act: -0.0000

Data Index: 199903 (The Pile)

Max Activating Token Index: 788

Text #4

Max Range: 7.8153. Min Range: -7.8153

Max Act: 6.1074. Min Act: -0.0000

Data Index: 1540576 (The Pile)

Max Activating Token Index: 285

Text #5

Max Range: 7.8153. Min Range: -7.8153

Max Act: 6.8150. Min Act: -0.0000

Data Index: 1079507 (The Pile)

Max Activating Token Index: 86

Text #6

Max Range: 7.8153. Min Range: -7.8153

Max Act: 4.1097. Min Act: -0.0000

Data Index: 1522264 (The Pile)

Max Activating Token Index: 95

Text #7

Max Range: 7.8153. Min Range: -7.8153

Max Act: 5.1434. Min Act: -0.0000

Data Index: 772694 (The Pile)

Max Activating Token Index: 29

Text #8

Max Range: 7.8153. Min Range: -7.8153

Max Act: 4.5994. Min Act: -0.0000

Data Index: 349949 (The Pile)

Max Activating Token Index: 52

Text #9

Max Range: 7.8153. Min Range: -7.8153

Max Act: 4.0664. Min Act: -0.0000

Data Index: 1888272 (The Pile)

Max Activating Token Index: 71

Text #10

Max Range: 7.8153. Min Range: -7.8153

Max Act: 4.0846. Min Act: -0.0000

Data Index: 1141038 (The Pile)

Max Activating Token Index: 67

Text #11

Max Range: 7.8153. Min Range: -7.8153

Max Act: 4.3312. Min Act: -0.0000

Data Index: 1494164 (The Pile)

Max Activating Token Index: 60

Text #12

Max Range: 7.8153. Min Range: -7.8153

Max Act: 4.3312. Min Act: -0.0000

Data Index: 205556 (The Pile)

Max Activating Token Index: 60

Text #13

Max Range: 7.8153. Min Range: -7.8153

Max Act: 4.0345. Min Act: -0.0000

Data Index: 869153 (The Pile)

Max Activating Token Index: 78

Text #14

Max Range: 7.8153. Min Range: -7.8153

Max Act: 3.7850. Min Act: -0.0000

Data Index: 1269310 (The Pile)

Max Activating Token Index: 81

Text #15

Max Range: 7.8153. Min Range: -7.8153

Max Act: 3.9908. Min Act: -0.0000

Data Index: 1534055 (The Pile)

Max Activating Token Index: 72

Text #16

Max Range: 7.8153. Min Range: -7.8153

Max Act: 3.9008. Min Act: -0.0000

Data Index: 1412438 (The Pile)

Max Activating Token Index: 51

Text #17

Max Range: 7.8153. Min Range: -7.8153

Max Act: 4.3614. Min Act: -0.0000

Data Index: 561794 (The Pile)

Max Activating Token Index: 685

Text #18

Max Range: 7.8153. Min Range: -7.8153

Max Act: 4.6216. Min Act: -0.0000

Data Index: 1803083 (The Pile)

Max Activating Token Index: 59

Text #19

Max Range: 7.8153. Min Range: -7.8153

Max Act: 4.6216. Min Act: -0.0000

Data Index: 674231 (The Pile)

Max Activating Token Index: 59