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

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

Neuron 2679 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9532. Min Range: -0.9532

Max Act: 0.9532. Min Act: -0.0003

Data Index: 447469 (C4 (Web Text))

Max Activating Token Index: 192

Text #1

Max Range: 0.9532. Min Range: -0.9532

Max Act: 0.9437. Min Act: -0.0003

Data Index: 442611 (C4 (Web Text))

Max Activating Token Index: 591

Text #2

Max Range: 0.9532. Min Range: -0.9532

Max Act: 0.9337. Min Act: -0.0003

Data Index: 1021388 (C4 (Web Text))

Max Activating Token Index: 218

Text #3

Max Range: 0.9532. Min Range: -0.9532

Max Act: 0.9239. Min Act: -0.0003

Data Index: 959614 (C4 (Web Text))

Max Activating Token Index: 696

Text #4

Max Range: 0.9532. Min Range: -0.9532

Max Act: 0.9070. Min Act: -0.0002

Data Index: 794398 (C4 (Web Text))

Max Activating Token Index: 317

Text #5

Max Range: 0.9532. Min Range: -0.9532

Max Act: 0.9096. Min Act: -0.0002

Data Index: 986571 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 0.9532. Min Range: -0.9532

Max Act: 0.8682. Min Act: -0.0003

Data Index: 515345 (C4 (Web Text))

Max Activating Token Index: 82

Text #7

Max Range: 0.9532. Min Range: -0.9532

Max Act: 0.8812. Min Act: -0.0003

Data Index: 305959 (C4 (Web Text))

Max Activating Token Index: 75

Text #8

Max Range: 0.9532. Min Range: -0.9532

Max Act: 0.8996. Min Act: -0.0003

Data Index: 750228 (C4 (Web Text))

Max Activating Token Index: 666

Text #9

Max Range: 0.9532. Min Range: -0.9532

Max Act: 0.8883. Min Act: -0.0003

Data Index: 247881 (C4 (Web Text))

Max Activating Token Index: 253

Text #10

Max Range: 0.9532. Min Range: -0.9532

Max Act: 0.8812. Min Act: -0.0003

Data Index: 436185 (C4 (Web Text))

Max Activating Token Index: 572

Text #11

Max Range: 0.9532. Min Range: -0.9532

Max Act: 0.8576. Min Act: -0.0002

Data Index: 778914 (C4 (Web Text))

Max Activating Token Index: 623

Text #12

Max Range: 0.9532. Min Range: -0.9532

Max Act: 0.8576. Min Act: -0.0003

Data Index: 109367 (C4 (Web Text))

Max Activating Token Index: 546

Text #13

Max Range: 0.9532. Min Range: -0.9532

Max Act: 0.8842. Min Act: -0.0003

Data Index: 20113 (C4 (Web Text))

Max Activating Token Index: 648

Text #14

Max Range: 0.9532. Min Range: -0.9532

Max Act: 0.8767. Min Act: -0.0003

Data Index: 828979 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 0.9532. Min Range: -0.9532

Max Act: 0.8720. Min Act: -0.0003

Data Index: 680748 (C4 (Web Text))

Max Activating Token Index: 401

Text #16

Max Range: 0.9532. Min Range: -0.9532

Max Act: 0.8710. Min Act: -0.0002

Data Index: 867442 (C4 (Web Text))

Max Activating Token Index: 848

Text #17

Max Range: 0.9532. Min Range: -0.9532

Max Act: 0.8467. Min Act: -0.0002

Data Index: 915195 (C4 (Web Text))

Max Activating Token Index: 668

Text #18

Max Range: 0.9532. Min Range: -0.9532

Max Act: 0.8431. Min Act: -0.0002

Data Index: 779952 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 0.9532. Min Range: -0.9532

Max Act: 0.8461. Min Act: -0.0002

Data Index: 1123806 (C4 (Web Text))

Max Activating Token Index: 786