Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1700 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0067. Min Act: -0.0006

Data Index: 1609233 (Python Code)

Max Activating Token Index: 930

Text #1

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0065. Min Act: -0.0006

Data Index: 1572049 (Python Code)

Max Activating Token Index: 861

Text #2

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0065. Min Act: -0.0006

Data Index: 1001556 (C4 (Web Text))

Max Activating Token Index: 626

Text #3

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0066. Min Act: -0.0006

Data Index: 1022753 (C4 (Web Text))

Max Activating Token Index: 842

Text #4

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0064. Min Act: -0.0006

Data Index: 1360284 (Python Code)

Max Activating Token Index: 621

Text #5

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0064. Min Act: -0.0006

Data Index: 1520722 (Python Code)

Max Activating Token Index: 26

Text #6

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0064. Min Act: -0.0005

Data Index: 1606420 (Python Code)

Max Activating Token Index: 736

Text #7

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0064. Min Act: -0.0006

Data Index: 33194 (C4 (Web Text))

Max Activating Token Index: 411

Text #8

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0064. Min Act: -0.0006

Data Index: 387793 (C4 (Web Text))

Max Activating Token Index: 431

Text #9

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0064. Min Act: -0.0006

Data Index: 1567206 (Python Code)

Max Activating Token Index: 460

Text #10

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0063. Min Act: -0.0005

Data Index: 1378542 (Python Code)

Max Activating Token Index: 242

Text #11

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0062. Min Act: -0.0006

Data Index: 1494256 (Python Code)

Max Activating Token Index: 790

Text #12

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0062. Min Act: -0.0006

Data Index: 679525 (C4 (Web Text))

Max Activating Token Index: 109

Text #13

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0063. Min Act: -0.0005

Data Index: 1064497 (C4 (Web Text))

Max Activating Token Index: 100

Text #14

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0062. Min Act: -0.0005

Data Index: 1360173 (Python Code)

Max Activating Token Index: 1015

Text #15

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0062. Min Act: -0.0006

Data Index: 400476 (C4 (Web Text))

Max Activating Token Index: 584

Text #16

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0062. Min Act: -0.0006

Data Index: 234086 (C4 (Web Text))

Max Activating Token Index: 945

Text #17

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0062. Min Act: -0.0006

Data Index: 1588997 (Python Code)

Max Activating Token Index: 731

Text #18

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0061. Min Act: -0.0006

Data Index: 318529 (C4 (Web Text))

Max Activating Token Index: 265

Text #19

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0061. Min Act: -0.0006

Data Index: 815453 (C4 (Web Text))

Max Activating Token Index: 164