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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1255 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3768. Min Range: -4.3768

Max Act: 4.3768. Min Act: -0.0000

Data Index: 1233477 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 4.3768. Min Range: -4.3768

Max Act: 4.2518. Min Act: -0.0000

Data Index: 213085 (C4 (Web Text))

Max Activating Token Index: 254

Text #2

Max Range: 4.3768. Min Range: -4.3768

Max Act: 4.2071. Min Act: -0.0000

Data Index: 96328 (C4 (Web Text))

Max Activating Token Index: 87

Text #3

Max Range: 4.3768. Min Range: -4.3768

Max Act: 3.8490. Min Act: -0.0000

Data Index: 1035014 (C4 (Web Text))

Max Activating Token Index: 629

Text #4

Max Range: 4.3768. Min Range: -4.3768

Max Act: 4.0089. Min Act: -0.0001

Data Index: 1233570 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 4.3768. Min Range: -4.3768

Max Act: 3.9917. Min Act: -0.0000

Data Index: 353450 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 4.3768. Min Range: -4.3768

Max Act: 3.5454. Min Act: -0.0000

Data Index: 77515 (C4 (Web Text))

Max Activating Token Index: 97

Text #7

Max Range: 4.3768. Min Range: -4.3768

Max Act: 3.8745. Min Act: -0.0000

Data Index: 338928 (C4 (Web Text))

Max Activating Token Index: 52

Text #8

Max Range: 4.3768. Min Range: -4.3768

Max Act: 3.8670. Min Act: -0.0001

Data Index: 802437 (C4 (Web Text))

Max Activating Token Index: 108

Text #9

Max Range: 4.3768. Min Range: -4.3768

Max Act: 3.6454. Min Act: -0.0000

Data Index: 975020 (C4 (Web Text))

Max Activating Token Index: 479

Text #10

Max Range: 4.3768. Min Range: -4.3768

Max Act: 3.6063. Min Act: -0.0000

Data Index: 568168 (C4 (Web Text))

Max Activating Token Index: 436

Text #11

Max Range: 4.3768. Min Range: -4.3768

Max Act: 3.5876. Min Act: -0.0001

Data Index: 253848 (C4 (Web Text))

Max Activating Token Index: 85

Text #12

Max Range: 4.3768. Min Range: -4.3768

Max Act: 3.8833. Min Act: -0.0000

Data Index: 1082153 (C4 (Web Text))

Max Activating Token Index: 103

Text #13

Max Range: 4.3768. Min Range: -4.3768

Max Act: 3.8374. Min Act: -0.0000

Data Index: 96631 (C4 (Web Text))

Max Activating Token Index: 147

Text #14

Max Range: 4.3768. Min Range: -4.3768

Max Act: 3.7161. Min Act: -0.0000

Data Index: 423883 (C4 (Web Text))

Max Activating Token Index: 315

Text #15

Max Range: 4.3768. Min Range: -4.3768

Max Act: 3.7004. Min Act: -0.0000

Data Index: 142596 (C4 (Web Text))

Max Activating Token Index: 210

Text #16

Max Range: 4.3768. Min Range: -4.3768

Max Act: 3.3650. Min Act: -0.0000

Data Index: 550186 (C4 (Web Text))

Max Activating Token Index: 258

Text #17

Max Range: 4.3768. Min Range: -4.3768

Max Act: 3.1914. Min Act: -0.0000

Data Index: 470135 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 4.3768. Min Range: -4.3768

Max Act: 3.3091. Min Act: -0.0000

Data Index: 1269401 (C4 (Web Text))

Max Activating Token Index: 744

Text #19

Max Range: 4.3768. Min Range: -4.3768

Max Act: 3.4383. Min Act: -0.0001

Data Index: 637955 (C4 (Web Text))

Max Activating Token Index: 174