Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 409 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2202. Min Range: -0.2202

Max Act: 0.2202. Min Act: -0.0003

Data Index: 643821 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 0.2202. Min Range: -0.2202

Max Act: 0.2052. Min Act: -0.0003

Data Index: 264216 (C4 (Web Text))

Max Activating Token Index: 827

Text #2

Max Range: 0.2202. Min Range: -0.2202

Max Act: 0.1899. Min Act: -0.0003

Data Index: 272999 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 0.2202. Min Range: -0.2202

Max Act: 0.1876. Min Act: -0.0003

Data Index: 120393 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 0.2202. Min Range: -0.2202

Max Act: 0.1834. Min Act: -0.0003

Data Index: 862962 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 0.2202. Min Range: -0.2202

Max Act: 0.1793. Min Act: -0.0003

Data Index: 379363 (C4 (Web Text))

Max Activating Token Index: 247

Text #6

Max Range: 0.2202. Min Range: -0.2202

Max Act: 0.1767. Min Act: -0.0003

Data Index: 425552 (C4 (Web Text))

Max Activating Token Index: 781

Text #7

Max Range: 0.2202. Min Range: -0.2202

Max Act: 0.1767. Min Act: -0.0002

Data Index: 679347 (C4 (Web Text))

Max Activating Token Index: 758

Text #8

Max Range: 0.2202. Min Range: -0.2202

Max Act: 0.1764. Min Act: -0.0003

Data Index: 567664 (C4 (Web Text))

Max Activating Token Index: 802

Text #9

Max Range: 0.2202. Min Range: -0.2202

Max Act: 0.1819. Min Act: -0.0003

Data Index: 1128221 (C4 (Web Text))

Max Activating Token Index: 359

Text #10

Max Range: 0.2202. Min Range: -0.2202

Max Act: 0.1726. Min Act: -0.0003

Data Index: 1253954 (C4 (Web Text))

Max Activating Token Index: 86

Text #11

Max Range: 0.2202. Min Range: -0.2202

Max Act: 0.1787. Min Act: -0.0003

Data Index: 1317621 (C4 (Web Text))

Max Activating Token Index: 654

Text #12

Max Range: 0.2202. Min Range: -0.2202

Max Act: 0.1718. Min Act: -0.0002

Data Index: 142692 (C4 (Web Text))

Max Activating Token Index: 737

Text #13

Max Range: 0.2202. Min Range: -0.2202

Max Act: 0.1712. Min Act: -0.0003

Data Index: 456944 (C4 (Web Text))

Max Activating Token Index: 161

Text #14

Max Range: 0.2202. Min Range: -0.2202

Max Act: 0.1772. Min Act: -0.0002

Data Index: 883966 (C4 (Web Text))

Max Activating Token Index: 818

Text #15

Max Range: 0.2202. Min Range: -0.2202

Max Act: 0.1689. Min Act: -0.0003

Data Index: 1303750 (C4 (Web Text))

Max Activating Token Index: 198

Text #16

Max Range: 0.2202. Min Range: -0.2202

Max Act: 0.1627. Min Act: -0.0003

Data Index: 438577 (C4 (Web Text))

Max Activating Token Index: 660

Text #17

Max Range: 0.2202. Min Range: -0.2202

Max Act: 0.1679. Min Act: -0.0003

Data Index: 448485 (C4 (Web Text))

Max Activating Token Index: 181

Text #18

Max Range: 0.2202. Min Range: -0.2202

Max Act: 0.1664. Min Act: -0.0003

Data Index: 801721 (C4 (Web Text))

Max Activating Token Index: 746

Text #19

Max Range: 0.2202. Min Range: -0.2202

Max Act: 0.1651. Min Act: -0.0003

Data Index: 1350702 (C4 (Web Text))

Max Activating Token Index: 239