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

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

Neuron 3408 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1470. Min Range: -1.1470

Max Act: 1.0953. Min Act: -0.0002

Data Index: 365476 (C4 (Web Text))

Max Activating Token Index: 444

Text #1

Max Range: 1.1470. Min Range: -1.1470

Max Act: 1.1470. Min Act: -0.0002

Data Index: 918317 (C4 (Web Text))

Max Activating Token Index: 198

Text #2

Max Range: 1.1470. Min Range: -1.1470

Max Act: 1.0250. Min Act: -0.0002

Data Index: 547965 (C4 (Web Text))

Max Activating Token Index: 914

Text #3

Max Range: 1.1470. Min Range: -1.1470

Max Act: 0.9150. Min Act: -0.0002

Data Index: 331357 (C4 (Web Text))

Max Activating Token Index: 978

Text #4

Max Range: 1.1470. Min Range: -1.1470

Max Act: 0.9828. Min Act: -0.0002

Data Index: 1109661 (C4 (Web Text))

Max Activating Token Index: 586

Text #5

Max Range: 1.1470. Min Range: -1.1470

Max Act: 0.9805. Min Act: -0.0002

Data Index: 626708 (C4 (Web Text))

Max Activating Token Index: 79

Text #6

Max Range: 1.1470. Min Range: -1.1470

Max Act: 0.9984. Min Act: -0.0002

Data Index: 318574 (C4 (Web Text))

Max Activating Token Index: 1007

Text #7

Max Range: 1.1470. Min Range: -1.1470

Max Act: 0.9279. Min Act: -0.0002

Data Index: 1279638 (C4 (Web Text))

Max Activating Token Index: 789

Text #8

Max Range: 1.1470. Min Range: -1.1470

Max Act: 1.0469. Min Act: -0.0002

Data Index: 929645 (C4 (Web Text))

Max Activating Token Index: 1000

Text #9

Max Range: 1.1470. Min Range: -1.1470

Max Act: 0.8708. Min Act: -0.0002

Data Index: 357895 (C4 (Web Text))

Max Activating Token Index: 915

Text #10

Max Range: 1.1470. Min Range: -1.1470

Max Act: 0.9889. Min Act: -0.0002

Data Index: 779700 (C4 (Web Text))

Max Activating Token Index: 6

Text #11

Max Range: 1.1470. Min Range: -1.1470

Max Act: 0.9726. Min Act: -0.0002

Data Index: 1091976 (C4 (Web Text))

Max Activating Token Index: 86

Text #12

Max Range: 1.1470. Min Range: -1.1470

Max Act: 0.8885. Min Act: -0.0002

Data Index: 795871 (C4 (Web Text))

Max Activating Token Index: 254

Text #13

Max Range: 1.1470. Min Range: -1.1470

Max Act: 0.9341. Min Act: -0.0002

Data Index: 623340 (C4 (Web Text))

Max Activating Token Index: 863

Text #14

Max Range: 1.1470. Min Range: -1.1470

Max Act: 0.9818. Min Act: -0.0002

Data Index: 840971 (C4 (Web Text))

Max Activating Token Index: 754

Text #15

Max Range: 1.1470. Min Range: -1.1470

Max Act: 1.0552. Min Act: -0.0002

Data Index: 459816 (C4 (Web Text))

Max Activating Token Index: 586

Text #16

Max Range: 1.1470. Min Range: -1.1470

Max Act: 0.9282. Min Act: -0.0002

Data Index: 186749 (C4 (Web Text))

Max Activating Token Index: 5

Text #17

Max Range: 1.1470. Min Range: -1.1470

Max Act: 0.8891. Min Act: -0.0002

Data Index: 960970 (C4 (Web Text))

Max Activating Token Index: 259

Text #18

Max Range: 1.1470. Min Range: -1.1470

Max Act: 0.8939. Min Act: -0.0002

Data Index: 1033540 (C4 (Web Text))

Max Activating Token Index: 1014

Text #19

Max Range: 1.1470. Min Range: -1.1470

Max Act: 0.8154. Min Act: -0.0002

Data Index: 801352 (C4 (Web Text))

Max Activating Token Index: 722