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

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

Neuron 5375 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: 3.6897. Min Range: -3.6897

Max Act: 3.6800. Min Act: -0.0000

Data Index: 829689 (C4 (Web Text))

Max Activating Token Index: 222

Text #1

Max Range: 3.6897. Min Range: -3.6897

Max Act: 3.6897. Min Act: -0.0000

Data Index: 123009 (C4 (Web Text))

Max Activating Token Index: 118

Text #2

Max Range: 3.6897. Min Range: -3.6897

Max Act: 3.4624. Min Act: -0.0000

Data Index: 1364247 (Python Code)

Max Activating Token Index: 525

Text #3

Max Range: 3.6897. Min Range: -3.6897

Max Act: 3.5005. Min Act: -0.0000

Data Index: 70913 (C4 (Web Text))

Max Activating Token Index: 1005

Text #4

Max Range: 3.6897. Min Range: -3.6897

Max Act: 3.3237. Min Act: -0.0000

Data Index: 1046333 (C4 (Web Text))

Max Activating Token Index: 681

Text #5

Max Range: 3.6897. Min Range: -3.6897

Max Act: 3.4599. Min Act: -0.0000

Data Index: 915240 (C4 (Web Text))

Max Activating Token Index: 798

Text #6

Max Range: 3.6897. Min Range: -3.6897

Max Act: 3.2745. Min Act: -0.0000

Data Index: 1138141 (C4 (Web Text))

Max Activating Token Index: 713

Text #7

Max Range: 3.6897. Min Range: -3.6897

Max Act: 3.4429. Min Act: -0.0000

Data Index: 879730 (C4 (Web Text))

Max Activating Token Index: 885

Text #8

Max Range: 3.6897. Min Range: -3.6897

Max Act: 3.2744. Min Act: -0.0000

Data Index: 618200 (C4 (Web Text))

Max Activating Token Index: 1022

Text #9

Max Range: 3.6897. Min Range: -3.6897

Max Act: 3.4077. Min Act: -0.0000

Data Index: 636370 (C4 (Web Text))

Max Activating Token Index: 643

Text #10

Max Range: 3.6897. Min Range: -3.6897

Max Act: 3.3991. Min Act: -0.0000

Data Index: 1405107 (Python Code)

Max Activating Token Index: 953

Text #11

Max Range: 3.6897. Min Range: -3.6897

Max Act: 3.3584. Min Act: -0.0000

Data Index: 870374 (C4 (Web Text))

Max Activating Token Index: 441

Text #12

Max Range: 3.6897. Min Range: -3.6897

Max Act: 3.5178. Min Act: -0.0000

Data Index: 185503 (C4 (Web Text))

Max Activating Token Index: 886

Text #13

Max Range: 3.6897. Min Range: -3.6897

Max Act: 3.3095. Min Act: -0.0000

Data Index: 48756 (C4 (Web Text))

Max Activating Token Index: 125

Text #14

Max Range: 3.6897. Min Range: -3.6897

Max Act: 3.2412. Min Act: -0.0000

Data Index: 950774 (C4 (Web Text))

Max Activating Token Index: 554

Text #15

Max Range: 3.6897. Min Range: -3.6897

Max Act: 3.2210. Min Act: -0.0000

Data Index: 374713 (C4 (Web Text))

Max Activating Token Index: 878

Text #16

Max Range: 3.6897. Min Range: -3.6897

Max Act: 3.2364. Min Act: -0.0000

Data Index: 716415 (C4 (Web Text))

Max Activating Token Index: 817

Text #17

Max Range: 3.6897. Min Range: -3.6897

Max Act: 3.2238. Min Act: -0.0000

Data Index: 207421 (C4 (Web Text))

Max Activating Token Index: 137

Text #18

Max Range: 3.6897. Min Range: -3.6897

Max Act: 3.2106. Min Act: -0.0000

Data Index: 445533 (C4 (Web Text))

Max Activating Token Index: 918

Text #19

Max Range: 3.6897. Min Range: -3.6897

Max Act: 3.1933. Min Act: -0.0000

Data Index: 327602 (C4 (Web Text))

Max Activating Token Index: 101