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

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

Neuron 5598 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.7733. Min Act: -0.0000

Data Index: 276995 (C4 (Web Text))

Max Activating Token Index: 210

Text #1

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.6917. Min Act: -0.0000

Data Index: 511836 (C4 (Web Text))

Max Activating Token Index: 901

Text #2

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.6805. Min Act: -0.0000

Data Index: 33017 (C4 (Web Text))

Max Activating Token Index: 322

Text #3

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.6326. Min Act: -0.0000

Data Index: 1183950 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.6288. Min Act: -0.0000

Data Index: 842266 (C4 (Web Text))

Max Activating Token Index: 625

Text #5

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.5826. Min Act: 0.0001

Data Index: 964825 (C4 (Web Text))

Max Activating Token Index: 62

Text #6

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.5562. Min Act: 0.0001

Data Index: 416831 (C4 (Web Text))

Max Activating Token Index: 699

Text #7

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.5326. Min Act: -0.0000

Data Index: 1039989 (C4 (Web Text))

Max Activating Token Index: 604

Text #8

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.5147. Min Act: -0.0000

Data Index: 383566 (C4 (Web Text))

Max Activating Token Index: 544

Text #9

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.5103. Min Act: -0.0000

Data Index: 362257 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.4957. Min Act: 0.0003

Data Index: 966368 (C4 (Web Text))

Max Activating Token Index: 461

Text #11

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.5073. Min Act: -0.0000

Data Index: 773274 (C4 (Web Text))

Max Activating Token Index: 275

Text #12

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.4878. Min Act: -0.0000

Data Index: 714874 (C4 (Web Text))

Max Activating Token Index: 878

Text #13

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.4712. Min Act: 0.0000

Data Index: 858239 (C4 (Web Text))

Max Activating Token Index: 747

Text #14

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.4687. Min Act: -0.0000

Data Index: 1089118 (C4 (Web Text))

Max Activating Token Index: 537

Text #15

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.4688. Min Act: -0.0000

Data Index: 147014 (C4 (Web Text))

Max Activating Token Index: 121

Text #16

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.4650. Min Act: 0.0000

Data Index: 1355229 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.4553. Min Act: -0.0000

Data Index: 596923 (C4 (Web Text))

Max Activating Token Index: 728

Text #18

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.4719. Min Act: -0.0000

Data Index: 1137071 (C4 (Web Text))

Max Activating Token Index: 702

Text #19

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.4488. Min Act: -0.0000

Data Index: 446529 (C4 (Web Text))

Max Activating Token Index: 652