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

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

Neuron 3789 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 9.4478. Min Range: -9.4478

Max Act: 9.4478. Min Act: -0.0001

Data Index: 1055736 (C4 (Web Text))

Max Activating Token Index: 736

Text #1

Max Range: 9.4478. Min Range: -9.4478

Max Act: 8.3987. Min Act: -0.0000

Data Index: 106261 (C4 (Web Text))

Max Activating Token Index: 964

Text #2

Max Range: 9.4478. Min Range: -9.4478

Max Act: 9.2210. Min Act: -0.0000

Data Index: 931706 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 9.4478. Min Range: -9.4478

Max Act: 9.0569. Min Act: -0.0000

Data Index: 621559 (C4 (Web Text))

Max Activating Token Index: 154

Text #4

Max Range: 9.4478. Min Range: -9.4478

Max Act: 8.5281. Min Act: -0.0001

Data Index: 254621 (C4 (Web Text))

Max Activating Token Index: 953

Text #5

Max Range: 9.4478. Min Range: -9.4478

Max Act: 8.3849. Min Act: -0.0000

Data Index: 1144643 (C4 (Web Text))

Max Activating Token Index: 182

Text #6

Max Range: 9.4478. Min Range: -9.4478

Max Act: 8.6607. Min Act: -0.0001

Data Index: 145990 (C4 (Web Text))

Max Activating Token Index: 196

Text #7

Max Range: 9.4478. Min Range: -9.4478

Max Act: 8.2495. Min Act: -0.0000

Data Index: 291403 (C4 (Web Text))

Max Activating Token Index: 195

Text #8

Max Range: 9.4478. Min Range: -9.4478

Max Act: 8.5073. Min Act: -0.0000

Data Index: 618405 (C4 (Web Text))

Max Activating Token Index: 64

Text #9

Max Range: 9.4478. Min Range: -9.4478

Max Act: 8.0114. Min Act: -0.0001

Data Index: 97315 (C4 (Web Text))

Max Activating Token Index: 551

Text #10

Max Range: 9.4478. Min Range: -9.4478

Max Act: 8.3533. Min Act: -0.0000

Data Index: 574738 (C4 (Web Text))

Max Activating Token Index: 158

Text #11

Max Range: 9.4478. Min Range: -9.4478

Max Act: 7.9956. Min Act: -0.0000

Data Index: 782825 (C4 (Web Text))

Max Activating Token Index: 419

Text #12

Max Range: 9.4478. Min Range: -9.4478

Max Act: 8.2807. Min Act: -0.0001

Data Index: 574683 (C4 (Web Text))

Max Activating Token Index: 873

Text #13

Max Range: 9.4478. Min Range: -9.4478

Max Act: 7.9458. Min Act: -0.0000

Data Index: 864983 (C4 (Web Text))

Max Activating Token Index: 729

Text #14

Max Range: 9.4478. Min Range: -9.4478

Max Act: 7.3665. Min Act: -0.0000

Data Index: 107760 (C4 (Web Text))

Max Activating Token Index: 936

Text #15

Max Range: 9.4478. Min Range: -9.4478

Max Act: 7.5122. Min Act: -0.0000

Data Index: 1264299 (C4 (Web Text))

Max Activating Token Index: 582

Text #16

Max Range: 9.4478. Min Range: -9.4478

Max Act: 7.8735. Min Act: -0.0000

Data Index: 1091475 (C4 (Web Text))

Max Activating Token Index: 521

Text #17

Max Range: 9.4478. Min Range: -9.4478

Max Act: 7.2255. Min Act: -0.0000

Data Index: 1305545 (C4 (Web Text))

Max Activating Token Index: 801

Text #18

Max Range: 9.4478. Min Range: -9.4478

Max Act: 7.5803. Min Act: -0.0000

Data Index: 221020 (C4 (Web Text))

Max Activating Token Index: 611

Text #19

Max Range: 9.4478. Min Range: -9.4478

Max Act: 7.7069. Min Act: -0.0000

Data Index: 899765 (C4 (Web Text))

Max Activating Token Index: 439