Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 328 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9944. Min Range: -0.9944

Max Act: 0.9944. Min Act: -0.0001

Data Index: 1613945 (Python Code)

Max Activating Token Index: 985

Text #1

Max Range: 0.9944. Min Range: -0.9944

Max Act: 0.7863. Min Act: -0.0001

Data Index: 1561040 (Python Code)

Max Activating Token Index: 851

Text #2

Max Range: 0.9944. Min Range: -0.9944

Max Act: 0.7967. Min Act: -0.0001

Data Index: 1438506 (Python Code)

Max Activating Token Index: 153

Text #3

Max Range: 0.9944. Min Range: -0.9944

Max Act: 0.7671. Min Act: -0.0001

Data Index: 1482797 (Python Code)

Max Activating Token Index: 810

Text #4

Max Range: 0.9944. Min Range: -0.9944

Max Act: 0.7742. Min Act: -0.0001

Data Index: 1583503 (Python Code)

Max Activating Token Index: 277

Text #5

Max Range: 0.9944. Min Range: -0.9944

Max Act: 0.7418. Min Act: -0.0001

Data Index: 1600678 (Python Code)

Max Activating Token Index: 339

Text #6

Max Range: 0.9944. Min Range: -0.9944

Max Act: 0.7350. Min Act: -0.0001

Data Index: 1457848 (Python Code)

Max Activating Token Index: 200

Text #7

Max Range: 0.9944. Min Range: -0.9944

Max Act: 0.7331. Min Act: -0.0001

Data Index: 1635861 (Python Code)

Max Activating Token Index: 932

Text #8

Max Range: 0.9944. Min Range: -0.9944

Max Act: 0.7253. Min Act: -0.0001

Data Index: 1373285 (Python Code)

Max Activating Token Index: 763

Text #9

Max Range: 0.9944. Min Range: -0.9944

Max Act: 0.7055. Min Act: -0.0001

Data Index: 1200978 (C4 (Web Text))

Max Activating Token Index: 592

Text #10

Max Range: 0.9944. Min Range: -0.9944

Max Act: 0.7531. Min Act: -0.0001

Data Index: 241666 (C4 (Web Text))

Max Activating Token Index: 665

Text #11

Max Range: 0.9944. Min Range: -0.9944

Max Act: 0.6954. Min Act: -0.0001

Data Index: 1579369 (Python Code)

Max Activating Token Index: 842

Text #12

Max Range: 0.9944. Min Range: -0.9944

Max Act: 0.7398. Min Act: -0.0001

Data Index: 1423781 (Python Code)

Max Activating Token Index: 844

Text #13

Max Range: 0.9944. Min Range: -0.9944

Max Act: 0.6687. Min Act: -0.0001

Data Index: 1418695 (Python Code)

Max Activating Token Index: 807

Text #14

Max Range: 0.9944. Min Range: -0.9944

Max Act: 0.6778. Min Act: -0.0001

Data Index: 1625849 (Python Code)

Max Activating Token Index: 272

Text #15

Max Range: 0.9944. Min Range: -0.9944

Max Act: 0.7067. Min Act: -0.0001

Data Index: 1590702 (Python Code)

Max Activating Token Index: 264

Text #16

Max Range: 0.9944. Min Range: -0.9944

Max Act: 0.6593. Min Act: -0.0001

Data Index: 1466818 (Python Code)

Max Activating Token Index: 542

Text #17

Max Range: 0.9944. Min Range: -0.9944

Max Act: 0.6963. Min Act: -0.0001

Data Index: 1513513 (Python Code)

Max Activating Token Index: 182

Text #18

Max Range: 0.9944. Min Range: -0.9944

Max Act: 0.6971. Min Act: -0.0000

Data Index: 1632264 (Python Code)

Max Activating Token Index: 689

Text #19

Max Range: 0.9944. Min Range: -0.9944

Max Act: 0.6941. Min Act: -0.0001

Data Index: 1553710 (Python Code)

Max Activating Token Index: 247