Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3762 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.9761. Min Range: -1.9761

Max Act: 1.9761. Min Act: -0.0000

Data Index: 425811 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 1.9761. Min Range: -1.9761

Max Act: 1.9077. Min Act: -0.0000

Data Index: 663123 (C4 (Web Text))

Max Activating Token Index: 969

Text #2

Max Range: 1.9761. Min Range: -1.9761

Max Act: 1.7103. Min Act: -0.0000

Data Index: 876714 (C4 (Web Text))

Max Activating Token Index: 282

Text #3

Max Range: 1.9761. Min Range: -1.9761

Max Act: 1.5553. Min Act: -0.0000

Data Index: 1118418 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 1.9761. Min Range: -1.9761

Max Act: 1.4998. Min Act: -0.0000

Data Index: 1607512 (Python Code)

Max Activating Token Index: 531

Text #5

Max Range: 1.9761. Min Range: -1.9761

Max Act: 1.4631. Min Act: -0.0000

Data Index: 940364 (C4 (Web Text))

Max Activating Token Index: 534

Text #6

Max Range: 1.9761. Min Range: -1.9761

Max Act: 1.4253. Min Act: -0.0000

Data Index: 668233 (C4 (Web Text))

Max Activating Token Index: 937

Text #7

Max Range: 1.9761. Min Range: -1.9761

Max Act: 1.5141. Min Act: -0.0000

Data Index: 982951 (C4 (Web Text))

Max Activating Token Index: 123

Text #8

Max Range: 1.9761. Min Range: -1.9761

Max Act: 1.5551. Min Act: -0.0000

Data Index: 624041 (C4 (Web Text))

Max Activating Token Index: 1019

Text #9

Max Range: 1.9761. Min Range: -1.9761

Max Act: 1.4468. Min Act: -0.0000

Data Index: 917911 (C4 (Web Text))

Max Activating Token Index: 127

Text #10

Max Range: 1.9761. Min Range: -1.9761

Max Act: 1.4887. Min Act: -0.0000

Data Index: 600513 (C4 (Web Text))

Max Activating Token Index: 442

Text #11

Max Range: 1.9761. Min Range: -1.9761

Max Act: 1.3294. Min Act: -0.0000

Data Index: 156565 (C4 (Web Text))

Max Activating Token Index: 996

Text #12

Max Range: 1.9761. Min Range: -1.9761

Max Act: 1.3922. Min Act: -0.0000

Data Index: 1656861 (Python Code)

Max Activating Token Index: 481

Text #13

Max Range: 1.9761. Min Range: -1.9761

Max Act: 1.3404. Min Act: -0.0000

Data Index: 1012961 (C4 (Web Text))

Max Activating Token Index: 403

Text #14

Max Range: 1.9761. Min Range: -1.9761

Max Act: 1.2908. Min Act: -0.0000

Data Index: 588256 (C4 (Web Text))

Max Activating Token Index: 810

Text #15

Max Range: 1.9761. Min Range: -1.9761

Max Act: 1.3710. Min Act: -0.0000

Data Index: 41723 (C4 (Web Text))

Max Activating Token Index: 121

Text #16

Max Range: 1.9761. Min Range: -1.9761

Max Act: 1.3998. Min Act: -0.0000

Data Index: 475634 (C4 (Web Text))

Max Activating Token Index: 130

Text #17

Max Range: 1.9761. Min Range: -1.9761

Max Act: 1.3493. Min Act: -0.0000

Data Index: 1390797 (Python Code)

Max Activating Token Index: 437

Text #18

Max Range: 1.9761. Min Range: -1.9761

Max Act: 1.1931. Min Act: -0.0000

Data Index: 709183 (C4 (Web Text))

Max Activating Token Index: 819

Text #19

Max Range: 1.9761. Min Range: -1.9761

Max Act: 1.3119. Min Act: -0.0000

Data Index: 831876 (C4 (Web Text))

Max Activating Token Index: 940