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

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

Neuron 1143 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4816. Min Range: -0.4816

Max Act: 0.4816. Min Act: -0.0000

Data Index: 769871 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 0.4816. Min Range: -0.4816

Max Act: 0.4147. Min Act: -0.0001

Data Index: 831014 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 0.4816. Min Range: -0.4816

Max Act: 0.4001. Min Act: -0.0001

Data Index: 1279732 (C4 (Web Text))

Max Activating Token Index: 13

Text #3

Max Range: 0.4816. Min Range: -0.4816

Max Act: 0.3941. Min Act: -0.0000

Data Index: 140872 (C4 (Web Text))

Max Activating Token Index: 17

Text #4

Max Range: 0.4816. Min Range: -0.4816

Max Act: 0.3763. Min Act: -0.0001

Data Index: 380250 (C4 (Web Text))

Max Activating Token Index: 33

Text #5

Max Range: 0.4816. Min Range: -0.4816

Max Act: 0.3821. Min Act: -0.0000

Data Index: 140022 (C4 (Web Text))

Max Activating Token Index: 77

Text #6

Max Range: 0.4816. Min Range: -0.4816

Max Act: 0.3931. Min Act: -0.0001

Data Index: 710725 (C4 (Web Text))

Max Activating Token Index: 46

Text #7

Max Range: 0.4816. Min Range: -0.4816

Max Act: 0.3785. Min Act: -0.0001

Data Index: 276540 (C4 (Web Text))

Max Activating Token Index: 656

Text #8

Max Range: 0.4816. Min Range: -0.4816

Max Act: 0.3582. Min Act: -0.0001

Data Index: 552160 (C4 (Web Text))

Max Activating Token Index: 194

Text #9

Max Range: 0.4816. Min Range: -0.4816

Max Act: 0.3660. Min Act: -0.0001

Data Index: 319376 (C4 (Web Text))

Max Activating Token Index: 36

Text #10

Max Range: 0.4816. Min Range: -0.4816

Max Act: 0.3261. Min Act: -0.0000

Data Index: 536334 (C4 (Web Text))

Max Activating Token Index: 846

Text #11

Max Range: 0.4816. Min Range: -0.4816

Max Act: 0.3731. Min Act: -0.0001

Data Index: 1312315 (C4 (Web Text))

Max Activating Token Index: 137

Text #12

Max Range: 0.4816. Min Range: -0.4816

Max Act: 0.3772. Min Act: -0.0001

Data Index: 144796 (C4 (Web Text))

Max Activating Token Index: 61

Text #13

Max Range: 0.4816. Min Range: -0.4816

Max Act: 0.3374. Min Act: -0.0001

Data Index: 956786 (C4 (Web Text))

Max Activating Token Index: 151

Text #14

Max Range: 0.4816. Min Range: -0.4816

Max Act: 0.3245. Min Act: -0.0001

Data Index: 1071973 (C4 (Web Text))

Max Activating Token Index: 937

Text #15

Max Range: 0.4816. Min Range: -0.4816

Max Act: 0.3003. Min Act: -0.0001

Data Index: 1056229 (C4 (Web Text))

Max Activating Token Index: 755

Text #16

Max Range: 0.4816. Min Range: -0.4816

Max Act: 0.3216. Min Act: -0.0001

Data Index: 615084 (C4 (Web Text))

Max Activating Token Index: 30

Text #17

Max Range: 0.4816. Min Range: -0.4816

Max Act: 0.3320. Min Act: -0.0001

Data Index: 660127 (C4 (Web Text))

Max Activating Token Index: 557

Text #18

Max Range: 0.4816. Min Range: -0.4816

Max Act: 0.3377. Min Act: -0.0000

Data Index: 783825 (C4 (Web Text))

Max Activating Token Index: 817

Text #19

Max Range: 0.4816. Min Range: -0.4816

Max Act: 0.3229. Min Act: -0.0001

Data Index: 616350 (C4 (Web Text))

Max Activating Token Index: 525