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

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

Neuron 346 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.4470. Min Act: -0.0001

Data Index: 412537 (C4 (Web Text))

Max Activating Token Index: 377

Text #1

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.4468. Min Act: -0.0001

Data Index: 755901 (C4 (Web Text))

Max Activating Token Index: 885

Text #2

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.4110. Min Act: -0.0001

Data Index: 720805 (C4 (Web Text))

Max Activating Token Index: 601

Text #3

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.2893. Min Act: -0.0001

Data Index: 1061569 (C4 (Web Text))

Max Activating Token Index: 506

Text #4

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.3982. Min Act: -0.0001

Data Index: 7955 (C4 (Web Text))

Max Activating Token Index: 156

Text #5

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.3733. Min Act: -0.0001

Data Index: 917315 (C4 (Web Text))

Max Activating Token Index: 752

Text #6

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.3414. Min Act: -0.0001

Data Index: 857406 (C4 (Web Text))

Max Activating Token Index: 663

Text #7

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.3490. Min Act: -0.0001

Data Index: 1195228 (C4 (Web Text))

Max Activating Token Index: 464

Text #8

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.3635. Min Act: -0.0001

Data Index: 894267 (C4 (Web Text))

Max Activating Token Index: 180

Text #9

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.3056. Min Act: -0.0001

Data Index: 779062 (C4 (Web Text))

Max Activating Token Index: 665

Text #10

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.2954. Min Act: -0.0001

Data Index: 902721 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.2939. Min Act: -0.0001

Data Index: 54156 (C4 (Web Text))

Max Activating Token Index: 563

Text #12

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.2866. Min Act: -0.0001

Data Index: 1106803 (C4 (Web Text))

Max Activating Token Index: 290

Text #13

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.2965. Min Act: -0.0001

Data Index: 547272 (C4 (Web Text))

Max Activating Token Index: 615

Text #14

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.3048. Min Act: -0.0001

Data Index: 1041529 (C4 (Web Text))

Max Activating Token Index: 943

Text #15

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.3214. Min Act: -0.0001

Data Index: 1065768 (C4 (Web Text))

Max Activating Token Index: 379

Text #16

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.2659. Min Act: -0.0001

Data Index: 17201 (C4 (Web Text))

Max Activating Token Index: 937

Text #17

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.2823. Min Act: -0.0001

Data Index: 256655 (C4 (Web Text))

Max Activating Token Index: 1010

Text #18

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.2853. Min Act: -0.0001

Data Index: 902126 (C4 (Web Text))

Max Activating Token Index: 101

Text #19

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.2632. Min Act: -0.0001

Data Index: 1266332 (C4 (Web Text))

Max Activating Token Index: 1015