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

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

Neuron 3674 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8973. Min Range: -0.8973

Max Act: 0.8973. Min Act: -0.0000

Data Index: 266693 (C4 (Web Text))

Max Activating Token Index: 918

Text #1

Max Range: 0.8973. Min Range: -0.8973

Max Act: 0.7279. Min Act: -0.0000

Data Index: 711440 (C4 (Web Text))

Max Activating Token Index: 615

Text #2

Max Range: 0.8973. Min Range: -0.8973

Max Act: 0.7480. Min Act: -0.0000

Data Index: 1276578 (C4 (Web Text))

Max Activating Token Index: 275

Text #3

Max Range: 0.8973. Min Range: -0.8973

Max Act: 0.7836. Min Act: -0.0000

Data Index: 281246 (C4 (Web Text))

Max Activating Token Index: 208

Text #4

Max Range: 0.8973. Min Range: -0.8973

Max Act: 0.6780. Min Act: -0.0000

Data Index: 1175023 (C4 (Web Text))

Max Activating Token Index: 452

Text #5

Max Range: 0.8973. Min Range: -0.8973

Max Act: 0.6334. Min Act: -0.0000

Data Index: 660084 (C4 (Web Text))

Max Activating Token Index: 235

Text #6

Max Range: 0.8973. Min Range: -0.8973

Max Act: 0.6547. Min Act: -0.0000

Data Index: 185841 (C4 (Web Text))

Max Activating Token Index: 303

Text #7

Max Range: 0.8973. Min Range: -0.8973

Max Act: 0.6198. Min Act: -0.0000

Data Index: 978643 (C4 (Web Text))

Max Activating Token Index: 404

Text #8

Max Range: 0.8973. Min Range: -0.8973

Max Act: 0.6810. Min Act: -0.0000

Data Index: 603968 (C4 (Web Text))

Max Activating Token Index: 972

Text #9

Max Range: 0.8973. Min Range: -0.8973

Max Act: 0.6178. Min Act: -0.0000

Data Index: 672265 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 0.8973. Min Range: -0.8973

Max Act: 0.6173. Min Act: -0.0000

Data Index: 1091787 (C4 (Web Text))

Max Activating Token Index: 177

Text #11

Max Range: 0.8973. Min Range: -0.8973

Max Act: 0.6083. Min Act: -0.0000

Data Index: 642817 (C4 (Web Text))

Max Activating Token Index: 587

Text #12

Max Range: 0.8973. Min Range: -0.8973

Max Act: 0.5531. Min Act: -0.0000

Data Index: 490415 (C4 (Web Text))

Max Activating Token Index: 644

Text #13

Max Range: 0.8973. Min Range: -0.8973

Max Act: 0.5805. Min Act: -0.0000

Data Index: 585130 (C4 (Web Text))

Max Activating Token Index: 303

Text #14

Max Range: 0.8973. Min Range: -0.8973

Max Act: 0.5449. Min Act: -0.0000

Data Index: 1324456 (C4 (Web Text))

Max Activating Token Index: 859

Text #15

Max Range: 0.8973. Min Range: -0.8973

Max Act: 0.5880. Min Act: -0.0000

Data Index: 799203 (C4 (Web Text))

Max Activating Token Index: 581

Text #16

Max Range: 0.8973. Min Range: -0.8973

Max Act: 0.5868. Min Act: -0.0000

Data Index: 1189629 (C4 (Web Text))

Max Activating Token Index: 582

Text #17

Max Range: 0.8973. Min Range: -0.8973

Max Act: 0.5136. Min Act: -0.0000

Data Index: 948497 (C4 (Web Text))

Max Activating Token Index: 734

Text #18

Max Range: 0.8973. Min Range: -0.8973

Max Act: 0.6181. Min Act: -0.0000

Data Index: 1265747 (C4 (Web Text))

Max Activating Token Index: 154

Text #19

Max Range: 0.8973. Min Range: -0.8973

Max Act: 0.5712. Min Act: -0.0000

Data Index: 1101791 (C4 (Web Text))

Max Activating Token Index: 974