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

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

Neuron 931 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2789. Min Range: -1.2789

Max Act: 1.2221. Min Act: -0.0001

Data Index: 658576 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 1.2789. Min Range: -1.2789

Max Act: 1.2789. Min Act: -0.0001

Data Index: 834936 (C4 (Web Text))

Max Activating Token Index: 299

Text #2

Max Range: 1.2789. Min Range: -1.2789

Max Act: 1.0649. Min Act: -0.0001

Data Index: 818000 (C4 (Web Text))

Max Activating Token Index: 663

Text #3

Max Range: 1.2789. Min Range: -1.2789

Max Act: 1.0536. Min Act: -0.0001

Data Index: 828858 (C4 (Web Text))

Max Activating Token Index: 524

Text #4

Max Range: 1.2789. Min Range: -1.2789

Max Act: 1.0474. Min Act: -0.0001

Data Index: 368261 (C4 (Web Text))

Max Activating Token Index: 460

Text #5

Max Range: 1.2789. Min Range: -1.2789

Max Act: 1.0076. Min Act: -0.0001

Data Index: 335806 (C4 (Web Text))

Max Activating Token Index: 385

Text #6

Max Range: 1.2789. Min Range: -1.2789

Max Act: 1.0325. Min Act: -0.0001

Data Index: 54269 (C4 (Web Text))

Max Activating Token Index: 974

Text #7

Max Range: 1.2789. Min Range: -1.2789

Max Act: 0.9402. Min Act: -0.0001

Data Index: 250261 (C4 (Web Text))

Max Activating Token Index: 708

Text #8

Max Range: 1.2789. Min Range: -1.2789

Max Act: 0.8949. Min Act: -0.0001

Data Index: 166065 (C4 (Web Text))

Max Activating Token Index: 436

Text #9

Max Range: 1.2789. Min Range: -1.2789

Max Act: 0.9381. Min Act: -0.0001

Data Index: 135087 (C4 (Web Text))

Max Activating Token Index: 75

Text #10

Max Range: 1.2789. Min Range: -1.2789

Max Act: 0.8803. Min Act: -0.0001

Data Index: 820296 (C4 (Web Text))

Max Activating Token Index: 788

Text #11

Max Range: 1.2789. Min Range: -1.2789

Max Act: 0.7674. Min Act: -0.0001

Data Index: 1033878 (C4 (Web Text))

Max Activating Token Index: 599

Text #12

Max Range: 1.2789. Min Range: -1.2789

Max Act: 0.8659. Min Act: -0.0001

Data Index: 747345 (C4 (Web Text))

Max Activating Token Index: 470

Text #13

Max Range: 1.2789. Min Range: -1.2789

Max Act: 0.7389. Min Act: -0.0001

Data Index: 1026060 (C4 (Web Text))

Max Activating Token Index: 712

Text #14

Max Range: 1.2789. Min Range: -1.2789

Max Act: 0.8559. Min Act: -0.0001

Data Index: 975688 (C4 (Web Text))

Max Activating Token Index: 29

Text #15

Max Range: 1.2789. Min Range: -1.2789

Max Act: 0.7946. Min Act: -0.0001

Data Index: 1257322 (C4 (Web Text))

Max Activating Token Index: 574

Text #16

Max Range: 1.2789. Min Range: -1.2789

Max Act: 0.8034. Min Act: -0.0001

Data Index: 73118 (C4 (Web Text))

Max Activating Token Index: 236

Text #17

Max Range: 1.2789. Min Range: -1.2789

Max Act: 0.7768. Min Act: -0.0001

Data Index: 252173 (C4 (Web Text))

Max Activating Token Index: 796

Text #18

Max Range: 1.2789. Min Range: -1.2789

Max Act: 0.7991. Min Act: -0.0001

Data Index: 1352064 (C4 (Web Text))

Max Activating Token Index: 869

Text #19

Max Range: 1.2789. Min Range: -1.2789

Max Act: 0.7383. Min Act: -0.0001

Data Index: 91413 (C4 (Web Text))

Max Activating Token Index: 211