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

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

Neuron 1839 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5354. Min Range: -0.5354

Max Act: 0.5354. Min Act: -0.0000

Data Index: 245719 (C4 (Web Text))

Max Activating Token Index: 205

Text #1

Max Range: 0.5354. Min Range: -0.5354

Max Act: 0.5181. Min Act: 0.0001

Data Index: 1650722 (Python Code)

Max Activating Token Index: 101

Text #2

Max Range: 0.5354. Min Range: -0.5354

Max Act: 0.4761. Min Act: -0.0000

Data Index: 1541240 (Python Code)

Max Activating Token Index: 1004

Text #3

Max Range: 0.5354. Min Range: -0.5354

Max Act: 0.5015. Min Act: -0.0000

Data Index: 1401603 (Python Code)

Max Activating Token Index: 197

Text #4

Max Range: 0.5354. Min Range: -0.5354

Max Act: 0.4326. Min Act: -0.0000

Data Index: 1367384 (Python Code)

Max Activating Token Index: 869

Text #5

Max Range: 0.5354. Min Range: -0.5354

Max Act: 0.4435. Min Act: -0.0000

Data Index: 585566 (C4 (Web Text))

Max Activating Token Index: 323

Text #6

Max Range: 0.5354. Min Range: -0.5354

Max Act: 0.4325. Min Act: -0.0000

Data Index: 1243194 (C4 (Web Text))

Max Activating Token Index: 26

Text #7

Max Range: 0.5354. Min Range: -0.5354

Max Act: 0.3871. Min Act: -0.0000

Data Index: 1363564 (Python Code)

Max Activating Token Index: 567

Text #8

Max Range: 0.5354. Min Range: -0.5354

Max Act: 0.4402. Min Act: -0.0000

Data Index: 1580886 (Python Code)

Max Activating Token Index: 994

Text #9

Max Range: 0.5354. Min Range: -0.5354

Max Act: 0.4262. Min Act: 0.0001

Data Index: 1609718 (Python Code)

Max Activating Token Index: 453

Text #10

Max Range: 0.5354. Min Range: -0.5354

Max Act: 0.4531. Min Act: -0.0000

Data Index: 1611077 (Python Code)

Max Activating Token Index: 779

Text #11

Max Range: 0.5354. Min Range: -0.5354

Max Act: 0.4079. Min Act: -0.0000

Data Index: 1405636 (Python Code)

Max Activating Token Index: 285

Text #12

Max Range: 0.5354. Min Range: -0.5354

Max Act: 0.3884. Min Act: -0.0000

Data Index: 1142636 (C4 (Web Text))

Max Activating Token Index: 127

Text #13

Max Range: 0.5354. Min Range: -0.5354

Max Act: 0.3957. Min Act: -0.0000

Data Index: 523592 (C4 (Web Text))

Max Activating Token Index: 962

Text #14

Max Range: 0.5354. Min Range: -0.5354

Max Act: 0.4046. Min Act: -0.0000

Data Index: 675237 (C4 (Web Text))

Max Activating Token Index: 18

Text #15

Max Range: 0.5354. Min Range: -0.5354

Max Act: 0.3761. Min Act: -0.0000

Data Index: 1421058 (Python Code)

Max Activating Token Index: 225

Text #16

Max Range: 0.5354. Min Range: -0.5354

Max Act: 0.3896. Min Act: -0.0000

Data Index: 1392868 (Python Code)

Max Activating Token Index: 705

Text #17

Max Range: 0.5354. Min Range: -0.5354

Max Act: 0.3381. Min Act: -0.0000

Data Index: 537951 (C4 (Web Text))

Max Activating Token Index: 971

Text #18

Max Range: 0.5354. Min Range: -0.5354

Max Act: 0.4237. Min Act: -0.0000

Data Index: 1568265 (Python Code)

Max Activating Token Index: 1019

Text #19

Max Range: 0.5354. Min Range: -0.5354

Max Act: 0.3843. Min Act: 0.0000

Data Index: 1440147 (Python Code)

Max Activating Token Index: 980