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

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

Neuron 6051 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: 0.6931. Min Range: -0.6931

Max Act: 0.6931. Min Act: -0.0000

Data Index: 106976 (C4 (Web Text))

Max Activating Token Index: 904

Text #1

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.5677. Min Act: -0.0000

Data Index: 1149913 (C4 (Web Text))

Max Activating Token Index: 851

Text #2

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.5879. Min Act: -0.0000

Data Index: 1398546 (Python Code)

Max Activating Token Index: 39

Text #3

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.5792. Min Act: -0.0000

Data Index: 1188515 (C4 (Web Text))

Max Activating Token Index: 343

Text #4

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.5486. Min Act: -0.0000

Data Index: 1423541 (Python Code)

Max Activating Token Index: 354

Text #5

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.5594. Min Act: -0.0000

Data Index: 1150606 (C4 (Web Text))

Max Activating Token Index: 849

Text #6

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.5509. Min Act: -0.0000

Data Index: 1440285 (Python Code)

Max Activating Token Index: 32

Text #7

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.5123. Min Act: -0.0000

Data Index: 1389167 (Python Code)

Max Activating Token Index: 56

Text #8

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.4967. Min Act: -0.0000

Data Index: 1473935 (Python Code)

Max Activating Token Index: 329

Text #9

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.5039. Min Act: -0.0000

Data Index: 1644535 (Python Code)

Max Activating Token Index: 265

Text #10

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.4888. Min Act: -0.0000

Data Index: 584467 (C4 (Web Text))

Max Activating Token Index: 876

Text #11

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.4985. Min Act: -0.0000

Data Index: 723495 (C4 (Web Text))

Max Activating Token Index: 327

Text #12

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.4911. Min Act: -0.0000

Data Index: 573214 (C4 (Web Text))

Max Activating Token Index: 636

Text #13

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.4605. Min Act: -0.0000

Data Index: 1196479 (C4 (Web Text))

Max Activating Token Index: 689

Text #14

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.5169. Min Act: -0.0000

Data Index: 787215 (C4 (Web Text))

Max Activating Token Index: 768

Text #15

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.4792. Min Act: -0.0000

Data Index: 54176 (C4 (Web Text))

Max Activating Token Index: 57

Text #16

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.4734. Min Act: -0.0000

Data Index: 1427118 (Python Code)

Max Activating Token Index: 959

Text #17

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.4881. Min Act: -0.0000

Data Index: 1531985 (Python Code)

Max Activating Token Index: 343

Text #18

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.4541. Min Act: -0.0000

Data Index: 908572 (C4 (Web Text))

Max Activating Token Index: 612

Text #19

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.4700. Min Act: -0.0000

Data Index: 1418671 (Python Code)

Max Activating Token Index: 535