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

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

Neuron 4665 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: 1.1948. Min Range: -1.1948

Max Act: 1.1485. Min Act: -0.0000

Data Index: 1036648 (C4 (Web Text))

Max Activating Token Index: 726

Text #1

Max Range: 1.1948. Min Range: -1.1948

Max Act: 1.1390. Min Act: -0.0000

Data Index: 750109 (C4 (Web Text))

Max Activating Token Index: 301

Text #2

Max Range: 1.1948. Min Range: -1.1948

Max Act: 1.1948. Min Act: -0.0000

Data Index: 241372 (C4 (Web Text))

Max Activating Token Index: 761

Text #3

Max Range: 1.1948. Min Range: -1.1948

Max Act: 1.0447. Min Act: -0.0000

Data Index: 72159 (C4 (Web Text))

Max Activating Token Index: 603

Text #4

Max Range: 1.1948. Min Range: -1.1948

Max Act: 0.9905. Min Act: -0.0000

Data Index: 368695 (C4 (Web Text))

Max Activating Token Index: 255

Text #5

Max Range: 1.1948. Min Range: -1.1948

Max Act: 1.0646. Min Act: -0.0000

Data Index: 339658 (C4 (Web Text))

Max Activating Token Index: 340

Text #6

Max Range: 1.1948. Min Range: -1.1948

Max Act: 1.1097. Min Act: -0.0000

Data Index: 880879 (C4 (Web Text))

Max Activating Token Index: 401

Text #7

Max Range: 1.1948. Min Range: -1.1948

Max Act: 0.9504. Min Act: -0.0000

Data Index: 576386 (C4 (Web Text))

Max Activating Token Index: 773

Text #8

Max Range: 1.1948. Min Range: -1.1948

Max Act: 1.0163. Min Act: -0.0000

Data Index: 1640145 (Python Code)

Max Activating Token Index: 356

Text #9

Max Range: 1.1948. Min Range: -1.1948

Max Act: 0.9526. Min Act: -0.0000

Data Index: 1236143 (C4 (Web Text))

Max Activating Token Index: 773

Text #10

Max Range: 1.1948. Min Range: -1.1948

Max Act: 0.9844. Min Act: -0.0000

Data Index: 1048679 (C4 (Web Text))

Max Activating Token Index: 87

Text #11

Max Range: 1.1948. Min Range: -1.1948

Max Act: 0.9432. Min Act: -0.0000

Data Index: 338333 (C4 (Web Text))

Max Activating Token Index: 459

Text #12

Max Range: 1.1948. Min Range: -1.1948

Max Act: 0.8976. Min Act: -0.0000

Data Index: 1363718 (Python Code)

Max Activating Token Index: 1003

Text #13

Max Range: 1.1948. Min Range: -1.1948

Max Act: 0.9073. Min Act: -0.0000

Data Index: 1591124 (Python Code)

Max Activating Token Index: 986

Text #14

Max Range: 1.1948. Min Range: -1.1948

Max Act: 0.9044. Min Act: -0.0000

Data Index: 176712 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 1.1948. Min Range: -1.1948

Max Act: 0.8868. Min Act: -0.0000

Data Index: 1486640 (Python Code)

Max Activating Token Index: 725

Text #16

Max Range: 1.1948. Min Range: -1.1948

Max Act: 0.9078. Min Act: -0.0000

Data Index: 59607 (C4 (Web Text))

Max Activating Token Index: 204

Text #17

Max Range: 1.1948. Min Range: -1.1948

Max Act: 0.8581. Min Act: -0.0000

Data Index: 437446 (C4 (Web Text))

Max Activating Token Index: 593

Text #18

Max Range: 1.1948. Min Range: -1.1948

Max Act: 0.8184. Min Act: -0.0000

Data Index: 1566610 (Python Code)

Max Activating Token Index: 748

Text #19

Max Range: 1.1948. Min Range: -1.1948

Max Act: 0.7706. Min Act: -0.0000

Data Index: 1575328 (Python Code)

Max Activating Token Index: 726