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

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

Neuron 4969 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9459. Min Range: -1.9459

Max Act: 1.9459. Min Act: -0.0000

Data Index: 1443948 (Python Code)

Max Activating Token Index: 147

Text #1

Max Range: 1.9459. Min Range: -1.9459

Max Act: 1.7559. Min Act: -0.0000

Data Index: 1627034 (Python Code)

Max Activating Token Index: 327

Text #2

Max Range: 1.9459. Min Range: -1.9459

Max Act: 1.6610. Min Act: -0.0000

Data Index: 1365250 (Python Code)

Max Activating Token Index: 96

Text #3

Max Range: 1.9459. Min Range: -1.9459

Max Act: 1.6967. Min Act: -0.0000

Data Index: 1507792 (Python Code)

Max Activating Token Index: 763

Text #4

Max Range: 1.9459. Min Range: -1.9459

Max Act: 1.7035. Min Act: -0.0000

Data Index: 215916 (C4 (Web Text))

Max Activating Token Index: 959

Text #5

Max Range: 1.9459. Min Range: -1.9459

Max Act: 1.5616. Min Act: -0.0000

Data Index: 753278 (C4 (Web Text))

Max Activating Token Index: 976

Text #6

Max Range: 1.9459. Min Range: -1.9459

Max Act: 1.6253. Min Act: -0.0000

Data Index: 274612 (C4 (Web Text))

Max Activating Token Index: 706

Text #7

Max Range: 1.9459. Min Range: -1.9459

Max Act: 1.4757. Min Act: -0.0000

Data Index: 1458871 (Python Code)

Max Activating Token Index: 396

Text #8

Max Range: 1.9459. Min Range: -1.9459

Max Act: 1.5494. Min Act: -0.0000

Data Index: 1514094 (Python Code)

Max Activating Token Index: 6

Text #9

Max Range: 1.9459. Min Range: -1.9459

Max Act: 1.4553. Min Act: -0.0000

Data Index: 992223 (C4 (Web Text))

Max Activating Token Index: 889

Text #10

Max Range: 1.9459. Min Range: -1.9459

Max Act: 1.4554. Min Act: -0.0000

Data Index: 1582637 (Python Code)

Max Activating Token Index: 55

Text #11

Max Range: 1.9459. Min Range: -1.9459

Max Act: 1.5207. Min Act: -0.0000

Data Index: 1459952 (Python Code)

Max Activating Token Index: 563

Text #12

Max Range: 1.9459. Min Range: -1.9459

Max Act: 1.4594. Min Act: -0.0000

Data Index: 1536882 (Python Code)

Max Activating Token Index: 228

Text #13

Max Range: 1.9459. Min Range: -1.9459

Max Act: 1.3569. Min Act: -0.0000

Data Index: 1378154 (Python Code)

Max Activating Token Index: 577

Text #14

Max Range: 1.9459. Min Range: -1.9459

Max Act: 1.4995. Min Act: -0.0000

Data Index: 1595564 (Python Code)

Max Activating Token Index: 38

Text #15

Max Range: 1.9459. Min Range: -1.9459

Max Act: 1.3724. Min Act: -0.0000

Data Index: 608117 (C4 (Web Text))

Max Activating Token Index: 799

Text #16

Max Range: 1.9459. Min Range: -1.9459

Max Act: 1.2442. Min Act: -0.0000

Data Index: 776050 (C4 (Web Text))

Max Activating Token Index: 902

Text #17

Max Range: 1.9459. Min Range: -1.9459

Max Act: 1.2050. Min Act: -0.0000

Data Index: 115314 (C4 (Web Text))

Max Activating Token Index: 924

Text #18

Max Range: 1.9459. Min Range: -1.9459

Max Act: 1.2646. Min Act: -0.0000

Data Index: 217673 (C4 (Web Text))

Max Activating Token Index: 121

Text #19

Max Range: 1.9459. Min Range: -1.9459

Max Act: 1.3392. Min Act: -0.0000

Data Index: 928075 (C4 (Web Text))

Max Activating Token Index: 19