Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4756 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.9640. Min Range: -3.9640

Max Act: 3.9640. Min Act: -0.0000

Data Index: 775249 (C4 (Web Text))

Max Activating Token Index: 745

Text #1

Max Range: 3.9640. Min Range: -3.9640

Max Act: 3.4305. Min Act: -0.0000

Data Index: 639953 (C4 (Web Text))

Max Activating Token Index: 939

Text #2

Max Range: 3.9640. Min Range: -3.9640

Max Act: 3.3701. Min Act: -0.0000

Data Index: 1315107 (C4 (Web Text))

Max Activating Token Index: 847

Text #3

Max Range: 3.9640. Min Range: -3.9640

Max Act: 3.2287. Min Act: -0.0000

Data Index: 1600685 (Python Code)

Max Activating Token Index: 170

Text #4

Max Range: 3.9640. Min Range: -3.9640

Max Act: 3.2806. Min Act: -0.0000

Data Index: 1201903 (C4 (Web Text))

Max Activating Token Index: 416

Text #5

Max Range: 3.9640. Min Range: -3.9640

Max Act: 2.9865. Min Act: -0.0000

Data Index: 1141408 (C4 (Web Text))

Max Activating Token Index: 1002

Text #6

Max Range: 3.9640. Min Range: -3.9640

Max Act: 2.8520. Min Act: 0.0000

Data Index: 1302859 (C4 (Web Text))

Max Activating Token Index: 485

Text #7

Max Range: 3.9640. Min Range: -3.9640

Max Act: 2.6969. Min Act: -0.0000

Data Index: 1447302 (Python Code)

Max Activating Token Index: 631

Text #8

Max Range: 3.9640. Min Range: -3.9640

Max Act: 3.1042. Min Act: -0.0000

Data Index: 1390855 (Python Code)

Max Activating Token Index: 977

Text #9

Max Range: 3.9640. Min Range: -3.9640

Max Act: 2.7376. Min Act: 0.0000

Data Index: 1256318 (C4 (Web Text))

Max Activating Token Index: 979

Text #10

Max Range: 3.9640. Min Range: -3.9640

Max Act: 2.6515. Min Act: -0.0000

Data Index: 111571 (C4 (Web Text))

Max Activating Token Index: 807

Text #11

Max Range: 3.9640. Min Range: -3.9640

Max Act: 2.4545. Min Act: -0.0000

Data Index: 1656967 (Python Code)

Max Activating Token Index: 407

Text #12

Max Range: 3.9640. Min Range: -3.9640

Max Act: 2.8547. Min Act: -0.0000

Data Index: 273686 (C4 (Web Text))

Max Activating Token Index: 108

Text #13

Max Range: 3.9640. Min Range: -3.9640

Max Act: 2.4857. Min Act: 0.0000

Data Index: 1175836 (C4 (Web Text))

Max Activating Token Index: 900

Text #14

Max Range: 3.9640. Min Range: -3.9640

Max Act: 2.6222. Min Act: 0.0000

Data Index: 654215 (C4 (Web Text))

Max Activating Token Index: 243

Text #15

Max Range: 3.9640. Min Range: -3.9640

Max Act: 2.7121. Min Act: -0.0000

Data Index: 628430 (C4 (Web Text))

Max Activating Token Index: 931

Text #16

Max Range: 3.9640. Min Range: -3.9640

Max Act: 2.8182. Min Act: -0.0000

Data Index: 1399551 (Python Code)

Max Activating Token Index: 791

Text #17

Max Range: 3.9640. Min Range: -3.9640

Max Act: 2.5355. Min Act: 0.0000

Data Index: 546775 (C4 (Web Text))

Max Activating Token Index: 665

Text #18

Max Range: 3.9640. Min Range: -3.9640

Max Act: 2.4996. Min Act: -0.0000

Data Index: 1052935 (C4 (Web Text))

Max Activating Token Index: 765

Text #19

Max Range: 3.9640. Min Range: -3.9640

Max Act: 2.3244. Min Act: -0.0000

Data Index: 632882 (C4 (Web Text))

Max Activating Token Index: 766