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

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

Neuron 2384 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: 2.3305. Min Range: -2.3305

Max Act: 2.3305. Min Act: -0.0000

Data Index: 1628499 (Python Code)

Max Activating Token Index: 659

Text #1

Max Range: 2.3305. Min Range: -2.3305

Max Act: 1.8293. Min Act: -0.0000

Data Index: 1653261 (Python Code)

Max Activating Token Index: 602

Text #2

Max Range: 2.3305. Min Range: -2.3305

Max Act: 1.9571. Min Act: -0.0000

Data Index: 1435416 (Python Code)

Max Activating Token Index: 505

Text #3

Max Range: 2.3305. Min Range: -2.3305

Max Act: 1.9433. Min Act: -0.0000

Data Index: 1533261 (Python Code)

Max Activating Token Index: 536

Text #4

Max Range: 2.3305. Min Range: -2.3305

Max Act: 1.5937. Min Act: -0.0000

Data Index: 1509822 (Python Code)

Max Activating Token Index: 867

Text #5

Max Range: 2.3305. Min Range: -2.3305

Max Act: 1.2002. Min Act: -0.0000

Data Index: 1157995 (C4 (Web Text))

Max Activating Token Index: 910

Text #6

Max Range: 2.3305. Min Range: -2.3305

Max Act: 0.9931. Min Act: -0.0000

Data Index: 980980 (C4 (Web Text))

Max Activating Token Index: 472

Text #7

Max Range: 2.3305. Min Range: -2.3305

Max Act: 0.9786. Min Act: -0.0000

Data Index: 728151 (C4 (Web Text))

Max Activating Token Index: 826

Text #8

Max Range: 2.3305. Min Range: -2.3305

Max Act: 0.9262. Min Act: -0.0000

Data Index: 1000415 (C4 (Web Text))

Max Activating Token Index: 870

Text #9

Max Range: 2.3305. Min Range: -2.3305

Max Act: 0.9543. Min Act: -0.0000

Data Index: 106121 (C4 (Web Text))

Max Activating Token Index: 16

Text #10

Max Range: 2.3305. Min Range: -2.3305

Max Act: 0.8624. Min Act: -0.0000

Data Index: 889998 (C4 (Web Text))

Max Activating Token Index: 166

Text #11

Max Range: 2.3305. Min Range: -2.3305

Max Act: 0.8292. Min Act: -0.0000

Data Index: 657262 (C4 (Web Text))

Max Activating Token Index: 883

Text #12

Max Range: 2.3305. Min Range: -2.3305

Max Act: 0.9063. Min Act: -0.0000

Data Index: 940508 (C4 (Web Text))

Max Activating Token Index: 692

Text #13

Max Range: 2.3305. Min Range: -2.3305

Max Act: 0.8905. Min Act: -0.0000

Data Index: 1114333 (C4 (Web Text))

Max Activating Token Index: 89

Text #14

Max Range: 2.3305. Min Range: -2.3305

Max Act: 0.9197. Min Act: -0.0000

Data Index: 243815 (C4 (Web Text))

Max Activating Token Index: 840

Text #15

Max Range: 2.3305. Min Range: -2.3305

Max Act: 0.8138. Min Act: -0.0000

Data Index: 1090138 (C4 (Web Text))

Max Activating Token Index: 156

Text #16

Max Range: 2.3305. Min Range: -2.3305

Max Act: 0.8402. Min Act: -0.0000

Data Index: 261441 (C4 (Web Text))

Max Activating Token Index: 49

Text #17

Max Range: 2.3305. Min Range: -2.3305

Max Act: 0.7692. Min Act: -0.0000

Data Index: 746862 (C4 (Web Text))

Max Activating Token Index: 327

Text #18

Max Range: 2.3305. Min Range: -2.3305

Max Act: 0.8362. Min Act: -0.0000

Data Index: 933681 (C4 (Web Text))

Max Activating Token Index: 95

Text #19

Max Range: 2.3305. Min Range: -2.3305

Max Act: 0.8139. Min Act: -0.0000

Data Index: 1320570 (C4 (Web Text))

Max Activating Token Index: 978