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

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

Neuron 4510 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0852. Min Range: -1.0852

Max Act: 1.0852. Min Act: -0.0000

Data Index: 858382 (C4 (Web Text))

Max Activating Token Index: 723

Text #1

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.9746. Min Act: -0.0000

Data Index: 671109 (C4 (Web Text))

Max Activating Token Index: 803

Text #2

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.9339. Min Act: -0.0000

Data Index: 686300 (C4 (Web Text))

Max Activating Token Index: 438

Text #3

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.8263. Min Act: -0.0000

Data Index: 951322 (C4 (Web Text))

Max Activating Token Index: 88

Text #4

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.6870. Min Act: -0.0000

Data Index: 1589504 (Python Code)

Max Activating Token Index: 263

Text #5

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.6367. Min Act: -0.0000

Data Index: 167912 (C4 (Web Text))

Max Activating Token Index: 255

Text #6

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.5583. Min Act: 0.0000

Data Index: 989403 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.5699. Min Act: -0.0000

Data Index: 906933 (C4 (Web Text))

Max Activating Token Index: 519

Text #8

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.5351. Min Act: -0.0000

Data Index: 1465831 (Python Code)

Max Activating Token Index: 256

Text #9

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.5023. Min Act: -0.0000

Data Index: 419818 (C4 (Web Text))

Max Activating Token Index: 680

Text #10

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.5155. Min Act: -0.0000

Data Index: 63170 (C4 (Web Text))

Max Activating Token Index: 898

Text #11

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.5026. Min Act: -0.0000

Data Index: 525504 (C4 (Web Text))

Max Activating Token Index: 858

Text #12

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.5183. Min Act: -0.0000

Data Index: 783728 (C4 (Web Text))

Max Activating Token Index: 33

Text #13

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.4827. Min Act: -0.0000

Data Index: 1103590 (C4 (Web Text))

Max Activating Token Index: 542

Text #14

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.6052. Min Act: -0.0000

Data Index: 480591 (C4 (Web Text))

Max Activating Token Index: 820

Text #15

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.4676. Min Act: -0.0000

Data Index: 998432 (C4 (Web Text))

Max Activating Token Index: 365

Text #16

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.4809. Min Act: -0.0000

Data Index: 515870 (C4 (Web Text))

Max Activating Token Index: 352

Text #17

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.4147. Min Act: -0.0000

Data Index: 827410 (C4 (Web Text))

Max Activating Token Index: 730

Text #18

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.4706. Min Act: -0.0000

Data Index: 84678 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.4666. Min Act: -0.0000

Data Index: 1033366 (C4 (Web Text))

Max Activating Token Index: 206