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

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

Neuron 418 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6819. Min Range: -3.6819

Max Act: 3.6819. Min Act: -0.0000

Data Index: 752917 (C4 (Web Text))

Max Activating Token Index: 286

Text #1

Max Range: 3.6819. Min Range: -3.6819

Max Act: 3.0312. Min Act: -0.0000

Data Index: 999893 (C4 (Web Text))

Max Activating Token Index: 853

Text #2

Max Range: 3.6819. Min Range: -3.6819

Max Act: 2.4100. Min Act: -0.0000

Data Index: 1078768 (C4 (Web Text))

Max Activating Token Index: 116

Text #3

Max Range: 3.6819. Min Range: -3.6819

Max Act: 2.1792. Min Act: -0.0000

Data Index: 1058894 (C4 (Web Text))

Max Activating Token Index: 809

Text #4

Max Range: 3.6819. Min Range: -3.6819

Max Act: 2.3597. Min Act: -0.0000

Data Index: 833597 (C4 (Web Text))

Max Activating Token Index: 607

Text #5

Max Range: 3.6819. Min Range: -3.6819

Max Act: 2.3418. Min Act: -0.0000

Data Index: 758353 (C4 (Web Text))

Max Activating Token Index: 507

Text #6

Max Range: 3.6819. Min Range: -3.6819

Max Act: 2.1070. Min Act: -0.0000

Data Index: 822957 (C4 (Web Text))

Max Activating Token Index: 460

Text #7

Max Range: 3.6819. Min Range: -3.6819

Max Act: 2.2943. Min Act: -0.0000

Data Index: 76316 (C4 (Web Text))

Max Activating Token Index: 312

Text #8

Max Range: 3.6819. Min Range: -3.6819

Max Act: 2.0560. Min Act: -0.0000

Data Index: 1249906 (C4 (Web Text))

Max Activating Token Index: 762

Text #9

Max Range: 3.6819. Min Range: -3.6819

Max Act: 1.9743. Min Act: -0.0000

Data Index: 767267 (C4 (Web Text))

Max Activating Token Index: 658

Text #10

Max Range: 3.6819. Min Range: -3.6819

Max Act: 1.9056. Min Act: -0.0000

Data Index: 405589 (C4 (Web Text))

Max Activating Token Index: 343

Text #11

Max Range: 3.6819. Min Range: -3.6819

Max Act: 1.8176. Min Act: -0.0000

Data Index: 759381 (C4 (Web Text))

Max Activating Token Index: 10

Text #12

Max Range: 3.6819. Min Range: -3.6819

Max Act: 1.8451. Min Act: -0.0000

Data Index: 22744 (C4 (Web Text))

Max Activating Token Index: 701

Text #13

Max Range: 3.6819. Min Range: -3.6819

Max Act: 1.8450. Min Act: -0.0000

Data Index: 447601 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 3.6819. Min Range: -3.6819

Max Act: 1.7768. Min Act: -0.0000

Data Index: 1238893 (C4 (Web Text))

Max Activating Token Index: 746

Text #15

Max Range: 3.6819. Min Range: -3.6819

Max Act: 1.6956. Min Act: -0.0000

Data Index: 540439 (C4 (Web Text))

Max Activating Token Index: 653

Text #16

Max Range: 3.6819. Min Range: -3.6819

Max Act: 1.7754. Min Act: -0.0000

Data Index: 1195721 (C4 (Web Text))

Max Activating Token Index: 468

Text #17

Max Range: 3.6819. Min Range: -3.6819

Max Act: 1.6199. Min Act: -0.0000

Data Index: 362677 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 3.6819. Min Range: -3.6819

Max Act: 1.3769. Min Act: -0.0000

Data Index: 1116358 (C4 (Web Text))

Max Activating Token Index: 360

Text #19

Max Range: 3.6819. Min Range: -3.6819

Max Act: 1.5071. Min Act: -0.0000

Data Index: 768692 (C4 (Web Text))

Max Activating Token Index: 338