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

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

Neuron 315 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: 1.8762. Min Range: -1.8762

Max Act: 1.8762. Min Act: -0.0001

Data Index: 521070 (C4 (Web Text))

Max Activating Token Index: 263

Text #1

Max Range: 1.8762. Min Range: -1.8762

Max Act: 1.8718. Min Act: -0.0000

Data Index: 880364 (C4 (Web Text))

Max Activating Token Index: 31

Text #2

Max Range: 1.8762. Min Range: -1.8762

Max Act: 1.6867. Min Act: -0.0000

Data Index: 625863 (C4 (Web Text))

Max Activating Token Index: 470

Text #3

Max Range: 1.8762. Min Range: -1.8762

Max Act: 1.6707. Min Act: -0.0000

Data Index: 726767 (C4 (Web Text))

Max Activating Token Index: 494

Text #4

Max Range: 1.8762. Min Range: -1.8762

Max Act: 1.5223. Min Act: -0.0001

Data Index: 426931 (C4 (Web Text))

Max Activating Token Index: 176

Text #5

Max Range: 1.8762. Min Range: -1.8762

Max Act: 1.1923. Min Act: -0.0001

Data Index: 195765 (C4 (Web Text))

Max Activating Token Index: 830

Text #6

Max Range: 1.8762. Min Range: -1.8762

Max Act: 1.1631. Min Act: -0.0000

Data Index: 1303280 (C4 (Web Text))

Max Activating Token Index: 908

Text #7

Max Range: 1.8762. Min Range: -1.8762

Max Act: 1.1164. Min Act: -0.0001

Data Index: 1359559 (C4 (Web Text))

Max Activating Token Index: 21

Text #8

Max Range: 1.8762. Min Range: -1.8762

Max Act: 1.1063. Min Act: -0.0000

Data Index: 937555 (C4 (Web Text))

Max Activating Token Index: 405

Text #9

Max Range: 1.8762. Min Range: -1.8762

Max Act: 0.9576. Min Act: -0.0000

Data Index: 410316 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 1.8762. Min Range: -1.8762

Max Act: 0.9972. Min Act: -0.0000

Data Index: 476677 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 1.8762. Min Range: -1.8762

Max Act: 1.0470. Min Act: -0.0001

Data Index: 1165663 (C4 (Web Text))

Max Activating Token Index: 719

Text #12

Max Range: 1.8762. Min Range: -1.8762

Max Act: 1.0152. Min Act: -0.0000

Data Index: 496474 (C4 (Web Text))

Max Activating Token Index: 229

Text #13

Max Range: 1.8762. Min Range: -1.8762

Max Act: 1.1137. Min Act: -0.0001

Data Index: 465605 (C4 (Web Text))

Max Activating Token Index: 335

Text #14

Max Range: 1.8762. Min Range: -1.8762

Max Act: 1.0567. Min Act: -0.0001

Data Index: 469634 (C4 (Web Text))

Max Activating Token Index: 407

Text #15

Max Range: 1.8762. Min Range: -1.8762

Max Act: 0.9437. Min Act: -0.0000

Data Index: 484844 (C4 (Web Text))

Max Activating Token Index: 138

Text #16

Max Range: 1.8762. Min Range: -1.8762

Max Act: 0.9830. Min Act: -0.0000

Data Index: 67906 (C4 (Web Text))

Max Activating Token Index: 561

Text #17

Max Range: 1.8762. Min Range: -1.8762

Max Act: 1.0637. Min Act: -0.0001

Data Index: 1089384 (C4 (Web Text))

Max Activating Token Index: 1015

Text #18

Max Range: 1.8762. Min Range: -1.8762

Max Act: 0.9190. Min Act: -0.0000

Data Index: 712595 (C4 (Web Text))

Max Activating Token Index: 296

Text #19

Max Range: 1.8762. Min Range: -1.8762

Max Act: 1.0697. Min Act: -0.0001

Data Index: 441099 (C4 (Web Text))

Max Activating Token Index: 765