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

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

Neuron 1592 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: 1.6137. Min Range: -1.6137

Max Act: 1.6137. Min Act: -0.0000

Data Index: 925747 (C4 (Web Text))

Max Activating Token Index: 864

Text #1

Max Range: 1.6137. Min Range: -1.6137

Max Act: 1.4887. Min Act: -0.0000

Data Index: 313034 (C4 (Web Text))

Max Activating Token Index: 448

Text #2

Max Range: 1.6137. Min Range: -1.6137

Max Act: 1.3889. Min Act: -0.0000

Data Index: 502568 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 1.6137. Min Range: -1.6137

Max Act: 1.3379. Min Act: -0.0000

Data Index: 1021889 (C4 (Web Text))

Max Activating Token Index: 126

Text #4

Max Range: 1.6137. Min Range: -1.6137

Max Act: 1.3708. Min Act: -0.0000

Data Index: 945587 (C4 (Web Text))

Max Activating Token Index: 868

Text #5

Max Range: 1.6137. Min Range: -1.6137

Max Act: 1.3504. Min Act: -0.0000

Data Index: 927847 (C4 (Web Text))

Max Activating Token Index: 245

Text #6

Max Range: 1.6137. Min Range: -1.6137

Max Act: 1.3305. Min Act: -0.0000

Data Index: 1169369 (C4 (Web Text))

Max Activating Token Index: 313

Text #7

Max Range: 1.6137. Min Range: -1.6137

Max Act: 1.2367. Min Act: -0.0000

Data Index: 25073 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 1.6137. Min Range: -1.6137

Max Act: 1.3072. Min Act: -0.0000

Data Index: 616104 (C4 (Web Text))

Max Activating Token Index: 695

Text #9

Max Range: 1.6137. Min Range: -1.6137

Max Act: 1.2203. Min Act: -0.0000

Data Index: 384054 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 1.6137. Min Range: -1.6137

Max Act: 1.1849. Min Act: -0.0000

Data Index: 649593 (C4 (Web Text))

Max Activating Token Index: 269

Text #11

Max Range: 1.6137. Min Range: -1.6137

Max Act: 1.2181. Min Act: -0.0000

Data Index: 917820 (C4 (Web Text))

Max Activating Token Index: 410

Text #12

Max Range: 1.6137. Min Range: -1.6137

Max Act: 1.1692. Min Act: -0.0000

Data Index: 299907 (C4 (Web Text))

Max Activating Token Index: 1003

Text #13

Max Range: 1.6137. Min Range: -1.6137

Max Act: 1.2632. Min Act: -0.0000

Data Index: 683047 (C4 (Web Text))

Max Activating Token Index: 15

Text #14

Max Range: 1.6137. Min Range: -1.6137

Max Act: 1.1866. Min Act: -0.0000

Data Index: 592100 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 1.6137. Min Range: -1.6137

Max Act: 1.1811. Min Act: -0.0000

Data Index: 1349435 (C4 (Web Text))

Max Activating Token Index: 404

Text #16

Max Range: 1.6137. Min Range: -1.6137

Max Act: 1.1703. Min Act: -0.0000

Data Index: 143719 (C4 (Web Text))

Max Activating Token Index: 124

Text #17

Max Range: 1.6137. Min Range: -1.6137

Max Act: 1.1574. Min Act: -0.0000

Data Index: 166546 (C4 (Web Text))

Max Activating Token Index: 370

Text #18

Max Range: 1.6137. Min Range: -1.6137

Max Act: 1.1909. Min Act: -0.0000

Data Index: 608253 (C4 (Web Text))

Max Activating Token Index: 1019

Text #19

Max Range: 1.6137. Min Range: -1.6137

Max Act: 1.1670. Min Act: -0.0000

Data Index: 526259 (C4 (Web Text))

Max Activating Token Index: 250