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

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

Neuron 1664 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: 0.5656. Min Range: -0.5656

Max Act: 0.5656. Min Act: -0.0001

Data Index: 721094 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 0.5656. Min Range: -0.5656

Max Act: 0.4568. Min Act: -0.0001

Data Index: 368188 (C4 (Web Text))

Max Activating Token Index: 440

Text #2

Max Range: 0.5656. Min Range: -0.5656

Max Act: 0.4192. Min Act: -0.0001

Data Index: 1133183 (C4 (Web Text))

Max Activating Token Index: 719

Text #3

Max Range: 0.5656. Min Range: -0.5656

Max Act: 0.4363. Min Act: -0.0001

Data Index: 785990 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 0.5656. Min Range: -0.5656

Max Act: 0.4481. Min Act: -0.0001

Data Index: 234248 (C4 (Web Text))

Max Activating Token Index: 41

Text #5

Max Range: 0.5656. Min Range: -0.5656

Max Act: 0.4056. Min Act: -0.0001

Data Index: 1248589 (C4 (Web Text))

Max Activating Token Index: 332

Text #6

Max Range: 0.5656. Min Range: -0.5656

Max Act: 0.3492. Min Act: -0.0001

Data Index: 747494 (C4 (Web Text))

Max Activating Token Index: 741

Text #7

Max Range: 0.5656. Min Range: -0.5656

Max Act: 0.3816. Min Act: -0.0001

Data Index: 584314 (C4 (Web Text))

Max Activating Token Index: 38

Text #8

Max Range: 0.5656. Min Range: -0.5656

Max Act: 0.4528. Min Act: -0.0001

Data Index: 776061 (C4 (Web Text))

Max Activating Token Index: 205

Text #9

Max Range: 0.5656. Min Range: -0.5656

Max Act: 0.3886. Min Act: -0.0001

Data Index: 1210956 (C4 (Web Text))

Max Activating Token Index: 376

Text #10

Max Range: 0.5656. Min Range: -0.5656

Max Act: 0.4299. Min Act: -0.0001

Data Index: 1103449 (C4 (Web Text))

Max Activating Token Index: 592

Text #11

Max Range: 0.5656. Min Range: -0.5656

Max Act: 0.4190. Min Act: -0.0001

Data Index: 287487 (C4 (Web Text))

Max Activating Token Index: 284

Text #12

Max Range: 0.5656. Min Range: -0.5656

Max Act: 0.3666. Min Act: -0.0001

Data Index: 894098 (C4 (Web Text))

Max Activating Token Index: 162

Text #13

Max Range: 0.5656. Min Range: -0.5656

Max Act: 0.3809. Min Act: -0.0001

Data Index: 500928 (C4 (Web Text))

Max Activating Token Index: 283

Text #14

Max Range: 0.5656. Min Range: -0.5656

Max Act: 0.4310. Min Act: -0.0001

Data Index: 397491 (C4 (Web Text))

Max Activating Token Index: 699

Text #15

Max Range: 0.5656. Min Range: -0.5656

Max Act: 0.3529. Min Act: -0.0001

Data Index: 965612 (C4 (Web Text))

Max Activating Token Index: 162

Text #16

Max Range: 0.5656. Min Range: -0.5656

Max Act: 0.3587. Min Act: -0.0001

Data Index: 664969 (C4 (Web Text))

Max Activating Token Index: 600

Text #17

Max Range: 0.5656. Min Range: -0.5656

Max Act: 0.3445. Min Act: -0.0001

Data Index: 155780 (C4 (Web Text))

Max Activating Token Index: 451

Text #18

Max Range: 0.5656. Min Range: -0.5656

Max Act: 0.2854. Min Act: -0.0001

Data Index: 957661 (C4 (Web Text))

Max Activating Token Index: 698

Text #19

Max Range: 0.5656. Min Range: -0.5656

Max Act: 0.3867. Min Act: -0.0001

Data Index: 667617 (C4 (Web Text))

Max Activating Token Index: 307