Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1021 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 3.9327. Min Range: -3.9327

Max Act: 3.9327. Min Act: -0.0002

Data Index: 872525 (C4 (Web Text))

Max Activating Token Index: 841

Text #1

Max Range: 3.9327. Min Range: -3.9327

Max Act: 2.0247. Min Act: -0.0002

Data Index: 1187822 (C4 (Web Text))

Max Activating Token Index: 203

Text #2

Max Range: 3.9327. Min Range: -3.9327

Max Act: 1.1733. Min Act: -0.0002

Data Index: 1493388 (Python Code)

Max Activating Token Index: 7

Text #3

Max Range: 3.9327. Min Range: -3.9327

Max Act: 0.4330. Min Act: -0.0002

Data Index: 61073 (C4 (Web Text))

Max Activating Token Index: 736

Text #4

Max Range: 3.9327. Min Range: -3.9327

Max Act: 1.3952. Min Act: -0.0002

Data Index: 345611 (C4 (Web Text))

Max Activating Token Index: 917

Text #5

Max Range: 3.9327. Min Range: -3.9327

Max Act: 0.5732. Min Act: -0.0002

Data Index: 685042 (C4 (Web Text))

Max Activating Token Index: 771

Text #6

Max Range: 3.9327. Min Range: -3.9327

Max Act: 1.0239. Min Act: -0.0002

Data Index: 1334662 (C4 (Web Text))

Max Activating Token Index: 815

Text #7

Max Range: 3.9327. Min Range: -3.9327

Max Act: 0.3354. Min Act: -0.0002

Data Index: 1556198 (Python Code)

Max Activating Token Index: 815

Text #8

Max Range: 3.9327. Min Range: -3.9327

Max Act: 0.0666. Min Act: -0.0002

Data Index: 1557033 (Python Code)

Max Activating Token Index: 980

Text #9

Max Range: 3.9327. Min Range: -3.9327

Max Act: 0.3116. Min Act: -0.0002

Data Index: 323549 (C4 (Web Text))

Max Activating Token Index: 753

Text #10

Max Range: 3.9327. Min Range: -3.9327

Max Act: 0.3172. Min Act: -0.0002

Data Index: 1514252 (Python Code)

Max Activating Token Index: 788

Text #11

Max Range: 3.9327. Min Range: -3.9327

Max Act: 0.3264. Min Act: -0.0002

Data Index: 1576111 (Python Code)

Max Activating Token Index: 11

Text #12

Max Range: 3.9327. Min Range: -3.9327

Max Act: 0.3615. Min Act: -0.0002

Data Index: 1565165 (Python Code)

Max Activating Token Index: 53

Text #13

Max Range: 3.9327. Min Range: -3.9327

Max Act: 0.2556. Min Act: -0.0002

Data Index: 275813 (C4 (Web Text))

Max Activating Token Index: 578

Text #14

Max Range: 3.9327. Min Range: -3.9327

Max Act: 0.2247. Min Act: -0.0002

Data Index: 1533536 (Python Code)

Max Activating Token Index: 44

Text #15

Max Range: 3.9327. Min Range: -3.9327

Max Act: 0.2359. Min Act: -0.0002

Data Index: 1212002 (C4 (Web Text))

Max Activating Token Index: 856

Text #16

Max Range: 3.9327. Min Range: -3.9327

Max Act: 0.1772. Min Act: -0.0001

Data Index: 1367310 (Python Code)

Max Activating Token Index: 528

Text #17

Max Range: 3.9327. Min Range: -3.9327

Max Act: 0.1612. Min Act: -0.0002

Data Index: 1541663 (Python Code)

Max Activating Token Index: 695

Text #18

Max Range: 3.9327. Min Range: -3.9327

Max Act: 0.1650. Min Act: 0.0002

Data Index: 1427090 (Python Code)

Max Activating Token Index: 676

Text #19

Max Range: 3.9327. Min Range: -3.9327

Max Act: 0.0110. Min Act: -0.0002

Data Index: 321196 (C4 (Web Text))

Max Activating Token Index: 981