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

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

Neuron 5415 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: 1.9817. Min Range: -1.9817

Max Act: 1.9817. Min Act: -0.0000

Data Index: 1390583 (Python Code)

Max Activating Token Index: 673

Text #1

Max Range: 1.9817. Min Range: -1.9817

Max Act: 1.8007. Min Act: -0.0000

Data Index: 1396532 (Python Code)

Max Activating Token Index: 86

Text #2

Max Range: 1.9817. Min Range: -1.9817

Max Act: 1.7809. Min Act: -0.0000

Data Index: 601956 (C4 (Web Text))

Max Activating Token Index: 988

Text #3

Max Range: 1.9817. Min Range: -1.9817

Max Act: 1.6707. Min Act: -0.0000

Data Index: 1519904 (Python Code)

Max Activating Token Index: 962

Text #4

Max Range: 1.9817. Min Range: -1.9817

Max Act: 1.7069. Min Act: -0.0000

Data Index: 1404887 (Python Code)

Max Activating Token Index: 824

Text #5

Max Range: 1.9817. Min Range: -1.9817

Max Act: 1.6947. Min Act: -0.0000

Data Index: 1488611 (Python Code)

Max Activating Token Index: 129

Text #6

Max Range: 1.9817. Min Range: -1.9817

Max Act: 1.4853. Min Act: -0.0000

Data Index: 1389885 (Python Code)

Max Activating Token Index: 721

Text #7

Max Range: 1.9817. Min Range: -1.9817

Max Act: 1.5585. Min Act: -0.0000

Data Index: 1480412 (Python Code)

Max Activating Token Index: 9

Text #8

Max Range: 1.9817. Min Range: -1.9817

Max Act: 1.4600. Min Act: -0.0000

Data Index: 1576461 (Python Code)

Max Activating Token Index: 268

Text #9

Max Range: 1.9817. Min Range: -1.9817

Max Act: 1.4535. Min Act: -0.0000

Data Index: 48024 (C4 (Web Text))

Max Activating Token Index: 659

Text #10

Max Range: 1.9817. Min Range: -1.9817

Max Act: 1.4453. Min Act: -0.0000

Data Index: 14653 (C4 (Web Text))

Max Activating Token Index: 464

Text #11

Max Range: 1.9817. Min Range: -1.9817

Max Act: 1.3432. Min Act: -0.0000

Data Index: 900894 (C4 (Web Text))

Max Activating Token Index: 318

Text #12

Max Range: 1.9817. Min Range: -1.9817

Max Act: 1.3317. Min Act: -0.0000

Data Index: 1487500 (Python Code)

Max Activating Token Index: 123

Text #13

Max Range: 1.9817. Min Range: -1.9817

Max Act: 1.4129. Min Act: -0.0000

Data Index: 1186777 (C4 (Web Text))

Max Activating Token Index: 442

Text #14

Max Range: 1.9817. Min Range: -1.9817

Max Act: 1.3878. Min Act: -0.0000

Data Index: 527975 (C4 (Web Text))

Max Activating Token Index: 621

Text #15

Max Range: 1.9817. Min Range: -1.9817

Max Act: 1.2900. Min Act: -0.0000

Data Index: 989635 (C4 (Web Text))

Max Activating Token Index: 748

Text #16

Max Range: 1.9817. Min Range: -1.9817

Max Act: 1.2760. Min Act: -0.0000

Data Index: 829497 (C4 (Web Text))

Max Activating Token Index: 808

Text #17

Max Range: 1.9817. Min Range: -1.9817

Max Act: 1.2615. Min Act: -0.0000

Data Index: 257875 (C4 (Web Text))

Max Activating Token Index: 433

Text #18

Max Range: 1.9817. Min Range: -1.9817

Max Act: 1.4159. Min Act: -0.0000

Data Index: 1567666 (Python Code)

Max Activating Token Index: 761

Text #19

Max Range: 1.9817. Min Range: -1.9817

Max Act: 1.3258. Min Act: -0.0000

Data Index: 596538 (C4 (Web Text))

Max Activating Token Index: 550