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

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

Neuron 3780 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5973. Min Range: -3.5973

Max Act: 3.5973. Min Act: -0.0000

Data Index: 1179541 (C4 (Web Text))

Max Activating Token Index: 268

Text #1

Max Range: 3.5973. Min Range: -3.5973

Max Act: 2.9780. Min Act: -0.0000

Data Index: 753962 (C4 (Web Text))

Max Activating Token Index: 857

Text #2

Max Range: 3.5973. Min Range: -3.5973

Max Act: 2.7899. Min Act: -0.0000

Data Index: 938138 (C4 (Web Text))

Max Activating Token Index: 954

Text #3

Max Range: 3.5973. Min Range: -3.5973

Max Act: 2.6017. Min Act: -0.0000

Data Index: 191759 (C4 (Web Text))

Max Activating Token Index: 825

Text #4

Max Range: 3.5973. Min Range: -3.5973

Max Act: 2.5352. Min Act: -0.0000

Data Index: 690755 (C4 (Web Text))

Max Activating Token Index: 883

Text #5

Max Range: 3.5973. Min Range: -3.5973

Max Act: 1.9999. Min Act: -0.0000

Data Index: 1080444 (C4 (Web Text))

Max Activating Token Index: 304

Text #6

Max Range: 3.5973. Min Range: -3.5973

Max Act: 2.5347. Min Act: -0.0000

Data Index: 529209 (C4 (Web Text))

Max Activating Token Index: 544

Text #7

Max Range: 3.5973. Min Range: -3.5973

Max Act: 2.4915. Min Act: -0.0000

Data Index: 552744 (C4 (Web Text))

Max Activating Token Index: 481

Text #8

Max Range: 3.5973. Min Range: -3.5973

Max Act: 2.2958. Min Act: -0.0000

Data Index: 1326663 (C4 (Web Text))

Max Activating Token Index: 498

Text #9

Max Range: 3.5973. Min Range: -3.5973

Max Act: 2.3151. Min Act: -0.0000

Data Index: 421320 (C4 (Web Text))

Max Activating Token Index: 492

Text #10

Max Range: 3.5973. Min Range: -3.5973

Max Act: 2.0392. Min Act: -0.0000

Data Index: 975955 (C4 (Web Text))

Max Activating Token Index: 324

Text #11

Max Range: 3.5973. Min Range: -3.5973

Max Act: 1.9635. Min Act: -0.0000

Data Index: 626464 (C4 (Web Text))

Max Activating Token Index: 510

Text #12

Max Range: 3.5973. Min Range: -3.5973

Max Act: 1.8361. Min Act: -0.0000

Data Index: 983594 (C4 (Web Text))

Max Activating Token Index: 178

Text #13

Max Range: 3.5973. Min Range: -3.5973

Max Act: 1.9301. Min Act: -0.0000

Data Index: 408298 (C4 (Web Text))

Max Activating Token Index: 738

Text #14

Max Range: 3.5973. Min Range: -3.5973

Max Act: 2.0303. Min Act: -0.0000

Data Index: 105483 (C4 (Web Text))

Max Activating Token Index: 276

Text #15

Max Range: 3.5973. Min Range: -3.5973

Max Act: 1.8513. Min Act: -0.0000

Data Index: 510099 (C4 (Web Text))

Max Activating Token Index: 144

Text #16

Max Range: 3.5973. Min Range: -3.5973

Max Act: 1.7065. Min Act: -0.0000

Data Index: 626292 (C4 (Web Text))

Max Activating Token Index: 700

Text #17

Max Range: 3.5973. Min Range: -3.5973

Max Act: 1.7995. Min Act: -0.0000

Data Index: 214348 (C4 (Web Text))

Max Activating Token Index: 949

Text #18

Max Range: 3.5973. Min Range: -3.5973

Max Act: 1.7663. Min Act: -0.0000

Data Index: 352 (C4 (Web Text))

Max Activating Token Index: 622

Text #19

Max Range: 3.5973. Min Range: -3.5973

Max Act: 1.6817. Min Act: -0.0000

Data Index: 697288 (C4 (Web Text))

Max Activating Token Index: 893