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

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

Neuron 1097 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.7411. Min Act: -0.0001

Data Index: 810613 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.7699. Min Act: -0.0001

Data Index: 356824 (C4 (Web Text))

Max Activating Token Index: 236

Text #2

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.6177. Min Act: -0.0001

Data Index: 397744 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.6945. Min Act: -0.0001

Data Index: 450046 (C4 (Web Text))

Max Activating Token Index: 854

Text #4

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.5927. Min Act: -0.0001

Data Index: 29226 (C4 (Web Text))

Max Activating Token Index: 600

Text #5

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.6543. Min Act: -0.0001

Data Index: 1204537 (C4 (Web Text))

Max Activating Token Index: 55

Text #6

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.5609. Min Act: -0.0001

Data Index: 325711 (C4 (Web Text))

Max Activating Token Index: 713

Text #7

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.6612. Min Act: -0.0001

Data Index: 326858 (C4 (Web Text))

Max Activating Token Index: 344

Text #8

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.5824. Min Act: -0.0001

Data Index: 220786 (C4 (Web Text))

Max Activating Token Index: 692

Text #9

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.5619. Min Act: -0.0001

Data Index: 822625 (C4 (Web Text))

Max Activating Token Index: 669

Text #10

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.5843. Min Act: -0.0001

Data Index: 1152582 (C4 (Web Text))

Max Activating Token Index: 715

Text #11

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.5469. Min Act: -0.0001

Data Index: 582421 (C4 (Web Text))

Max Activating Token Index: 144

Text #12

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.5400. Min Act: -0.0001

Data Index: 208275 (C4 (Web Text))

Max Activating Token Index: 338

Text #13

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.5757. Min Act: -0.0001

Data Index: 784362 (C4 (Web Text))

Max Activating Token Index: 761

Text #14

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.5330. Min Act: -0.0001

Data Index: 876895 (C4 (Web Text))

Max Activating Token Index: 48

Text #15

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.5467. Min Act: -0.0001

Data Index: 1309336 (C4 (Web Text))

Max Activating Token Index: 82

Text #16

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.5782. Min Act: -0.0001

Data Index: 825519 (C4 (Web Text))

Max Activating Token Index: 991

Text #17

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.5277. Min Act: -0.0001

Data Index: 479093 (C4 (Web Text))

Max Activating Token Index: 962

Text #18

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.5370. Min Act: -0.0001

Data Index: 1144979 (C4 (Web Text))

Max Activating Token Index: 958

Text #19

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.5348. Min Act: -0.0001

Data Index: 955879 (C4 (Web Text))

Max Activating Token Index: 280