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

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

Neuron 1538 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.2160. Min Act: -0.0002

Data Index: 1595594 (Python Code)

Max Activating Token Index: 912

Text #1

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.2021. Min Act: -0.0002

Data Index: 238951 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.1883. Min Act: -0.0002

Data Index: 743863 (C4 (Web Text))

Max Activating Token Index: 131

Text #3

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.1932. Min Act: -0.0002

Data Index: 33089 (C4 (Web Text))

Max Activating Token Index: 56

Text #4

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.1893. Min Act: -0.0002

Data Index: 1098532 (C4 (Web Text))

Max Activating Token Index: 402

Text #5

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.1873. Min Act: -0.0002

Data Index: 371059 (C4 (Web Text))

Max Activating Token Index: 32

Text #6

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.1735. Min Act: -0.0002

Data Index: 131105 (C4 (Web Text))

Max Activating Token Index: 314

Text #7

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.1713. Min Act: -0.0002

Data Index: 1258390 (C4 (Web Text))

Max Activating Token Index: 745

Text #8

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.1825. Min Act: -0.0002

Data Index: 1555486 (Python Code)

Max Activating Token Index: 519

Text #9

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.1815. Min Act: -0.0002

Data Index: 196407 (C4 (Web Text))

Max Activating Token Index: 867

Text #10

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.1477. Min Act: -0.0002

Data Index: 493516 (C4 (Web Text))

Max Activating Token Index: 277

Text #11

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.1864. Min Act: -0.0002

Data Index: 1079822 (C4 (Web Text))

Max Activating Token Index: 233

Text #12

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.1857. Min Act: -0.0002

Data Index: 193358 (C4 (Web Text))

Max Activating Token Index: 892

Text #13

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.1783. Min Act: -0.0002

Data Index: 1118103 (C4 (Web Text))

Max Activating Token Index: 138

Text #14

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.1811. Min Act: -0.0002

Data Index: 739577 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.1646. Min Act: -0.0002

Data Index: 385274 (C4 (Web Text))

Max Activating Token Index: 128

Text #16

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.1693. Min Act: -0.0002

Data Index: 33286 (C4 (Web Text))

Max Activating Token Index: 884

Text #17

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.1731. Min Act: -0.0002

Data Index: 425246 (C4 (Web Text))

Max Activating Token Index: 664

Text #18

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.1443. Min Act: -0.0002

Data Index: 157499 (C4 (Web Text))

Max Activating Token Index: 713

Text #19

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.1522. Min Act: -0.0002

Data Index: 1047381 (C4 (Web Text))

Max Activating Token Index: 515