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

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

Neuron 3831 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9188. Min Range: -0.9188

Max Act: 0.9188. Min Act: -0.0000

Data Index: 1641685 (Python Code)

Max Activating Token Index: 272

Text #1

Max Range: 0.9188. Min Range: -0.9188

Max Act: 0.7638. Min Act: -0.0001

Data Index: 26519 (C4 (Web Text))

Max Activating Token Index: 510

Text #2

Max Range: 0.9188. Min Range: -0.9188

Max Act: 0.7584. Min Act: -0.0001

Data Index: 494323 (C4 (Web Text))

Max Activating Token Index: 102

Text #3

Max Range: 0.9188. Min Range: -0.9188

Max Act: 0.7309. Min Act: -0.0000

Data Index: 243037 (C4 (Web Text))

Max Activating Token Index: 137

Text #4

Max Range: 0.9188. Min Range: -0.9188

Max Act: 0.7050. Min Act: -0.0000

Data Index: 1600621 (Python Code)

Max Activating Token Index: 567

Text #5

Max Range: 0.9188. Min Range: -0.9188

Max Act: 0.6760. Min Act: -0.0001

Data Index: 1049583 (C4 (Web Text))

Max Activating Token Index: 730

Text #6

Max Range: 0.9188. Min Range: -0.9188

Max Act: 0.6624. Min Act: -0.0000

Data Index: 444077 (C4 (Web Text))

Max Activating Token Index: 592

Text #7

Max Range: 0.9188. Min Range: -0.9188

Max Act: 0.6749. Min Act: -0.0001

Data Index: 191700 (C4 (Web Text))

Max Activating Token Index: 723

Text #8

Max Range: 0.9188. Min Range: -0.9188

Max Act: 0.7043. Min Act: -0.0001

Data Index: 222857 (C4 (Web Text))

Max Activating Token Index: 751

Text #9

Max Range: 0.9188. Min Range: -0.9188

Max Act: 0.6833. Min Act: -0.0001

Data Index: 49809 (C4 (Web Text))

Max Activating Token Index: 772

Text #10

Max Range: 0.9188. Min Range: -0.9188

Max Act: 0.6638. Min Act: -0.0000

Data Index: 1584401 (Python Code)

Max Activating Token Index: 454

Text #11

Max Range: 0.9188. Min Range: -0.9188

Max Act: 0.6641. Min Act: -0.0000

Data Index: 1388488 (Python Code)

Max Activating Token Index: 93

Text #12

Max Range: 0.9188. Min Range: -0.9188

Max Act: 0.6611. Min Act: -0.0001

Data Index: 1068982 (C4 (Web Text))

Max Activating Token Index: 647

Text #13

Max Range: 0.9188. Min Range: -0.9188

Max Act: 0.6598. Min Act: -0.0001

Data Index: 422280 (C4 (Web Text))

Max Activating Token Index: 581

Text #14

Max Range: 0.9188. Min Range: -0.9188

Max Act: 0.6793. Min Act: -0.0001

Data Index: 147384 (C4 (Web Text))

Max Activating Token Index: 888

Text #15

Max Range: 0.9188. Min Range: -0.9188

Max Act: 0.6603. Min Act: -0.0001

Data Index: 739627 (C4 (Web Text))

Max Activating Token Index: 766

Text #16

Max Range: 0.9188. Min Range: -0.9188

Max Act: 0.6204. Min Act: -0.0001

Data Index: 408611 (C4 (Web Text))

Max Activating Token Index: 655

Text #17

Max Range: 0.9188. Min Range: -0.9188

Max Act: 0.6177. Min Act: -0.0001

Data Index: 259808 (C4 (Web Text))

Max Activating Token Index: 995

Text #18

Max Range: 0.9188. Min Range: -0.9188

Max Act: 0.6760. Min Act: -0.0001

Data Index: 1084749 (C4 (Web Text))

Max Activating Token Index: 979

Text #19

Max Range: 0.9188. Min Range: -0.9188

Max Act: 0.6131. Min Act: -0.0000

Data Index: 1634650 (Python Code)

Max Activating Token Index: 567