Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 556 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5216. Min Range: -1.5216

Max Act: 1.5216. Min Act: -0.0002

Data Index: 179025 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 1.5216. Min Range: -1.5216

Max Act: 1.3834. Min Act: -0.0002

Data Index: 379581 (C4 (Web Text))

Max Activating Token Index: 79

Text #2

Max Range: 1.5216. Min Range: -1.5216

Max Act: 1.2360. Min Act: -0.0002

Data Index: 911320 (C4 (Web Text))

Max Activating Token Index: 648

Text #3

Max Range: 1.5216. Min Range: -1.5216

Max Act: 1.3611. Min Act: -0.0002

Data Index: 1037083 (C4 (Web Text))

Max Activating Token Index: 65

Text #4

Max Range: 1.5216. Min Range: -1.5216

Max Act: 1.2875. Min Act: -0.0001

Data Index: 1031462 (C4 (Web Text))

Max Activating Token Index: 885

Text #5

Max Range: 1.5216. Min Range: -1.5216

Max Act: 1.3060. Min Act: -0.0002

Data Index: 811734 (C4 (Web Text))

Max Activating Token Index: 567

Text #6

Max Range: 1.5216. Min Range: -1.5216

Max Act: 1.5053. Min Act: -0.0002

Data Index: 905807 (C4 (Web Text))

Max Activating Token Index: 899

Text #7

Max Range: 1.5216. Min Range: -1.5216

Max Act: 1.3069. Min Act: -0.0001

Data Index: 673189 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 1.5216. Min Range: -1.5216

Max Act: 1.2875. Min Act: -0.0002

Data Index: 165781 (C4 (Web Text))

Max Activating Token Index: 651

Text #9

Max Range: 1.5216. Min Range: -1.5216

Max Act: 1.0861. Min Act: -0.0001

Data Index: 599124 (C4 (Web Text))

Max Activating Token Index: 763

Text #10

Max Range: 1.5216. Min Range: -1.5216

Max Act: 1.1592. Min Act: -0.0001

Data Index: 118053 (C4 (Web Text))

Max Activating Token Index: 635

Text #11

Max Range: 1.5216. Min Range: -1.5216

Max Act: 1.1966. Min Act: -0.0002

Data Index: 835261 (C4 (Web Text))

Max Activating Token Index: 560

Text #12

Max Range: 1.5216. Min Range: -1.5216

Max Act: 1.0400. Min Act: -0.0002

Data Index: 713908 (C4 (Web Text))

Max Activating Token Index: 953

Text #13

Max Range: 1.5216. Min Range: -1.5216

Max Act: 1.1760. Min Act: -0.0002

Data Index: 959669 (C4 (Web Text))

Max Activating Token Index: 289

Text #14

Max Range: 1.5216. Min Range: -1.5216

Max Act: 1.2163. Min Act: -0.0001

Data Index: 44556 (C4 (Web Text))

Max Activating Token Index: 390

Text #15

Max Range: 1.5216. Min Range: -1.5216

Max Act: 1.1024. Min Act: -0.0002

Data Index: 984553 (C4 (Web Text))

Max Activating Token Index: 31

Text #16

Max Range: 1.5216. Min Range: -1.5216

Max Act: 1.0735. Min Act: -0.0002

Data Index: 130540 (C4 (Web Text))

Max Activating Token Index: 673

Text #17

Max Range: 1.5216. Min Range: -1.5216

Max Act: 1.1292. Min Act: -0.0001

Data Index: 168962 (C4 (Web Text))

Max Activating Token Index: 163

Text #18

Max Range: 1.5216. Min Range: -1.5216

Max Act: 1.0870. Min Act: -0.0001

Data Index: 212578 (C4 (Web Text))

Max Activating Token Index: 834

Text #19

Max Range: 1.5216. Min Range: -1.5216

Max Act: 1.0910. Min Act: -0.0002

Data Index: 1340255 (C4 (Web Text))

Max Activating Token Index: 281