Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1141 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.6111. Min Range: -1.6111

Max Act: 1.6111. Min Act: -0.0000

Data Index: 280390 (C4 (Web Text))

Max Activating Token Index: 163

Text #1

Max Range: 1.6111. Min Range: -1.6111

Max Act: 1.5635. Min Act: -0.0000

Data Index: 1003145 (C4 (Web Text))

Max Activating Token Index: 590

Text #2

Max Range: 1.6111. Min Range: -1.6111

Max Act: 1.3892. Min Act: -0.0000

Data Index: 85574 (C4 (Web Text))

Max Activating Token Index: 537

Text #3

Max Range: 1.6111. Min Range: -1.6111

Max Act: 1.4201. Min Act: -0.0000

Data Index: 879853 (C4 (Web Text))

Max Activating Token Index: 469

Text #4

Max Range: 1.6111. Min Range: -1.6111

Max Act: 1.3761. Min Act: -0.0000

Data Index: 454795 (C4 (Web Text))

Max Activating Token Index: 1022

Text #5

Max Range: 1.6111. Min Range: -1.6111

Max Act: 1.3710. Min Act: -0.0000

Data Index: 867140 (C4 (Web Text))

Max Activating Token Index: 216

Text #6

Max Range: 1.6111. Min Range: -1.6111

Max Act: 1.3531. Min Act: -0.0000

Data Index: 138740 (C4 (Web Text))

Max Activating Token Index: 138

Text #7

Max Range: 1.6111. Min Range: -1.6111

Max Act: 1.3859. Min Act: -0.0000

Data Index: 540017 (C4 (Web Text))

Max Activating Token Index: 646

Text #8

Max Range: 1.6111. Min Range: -1.6111

Max Act: 1.3188. Min Act: -0.0000

Data Index: 644311 (C4 (Web Text))

Max Activating Token Index: 502

Text #9

Max Range: 1.6111. Min Range: -1.6111

Max Act: 1.2502. Min Act: -0.0000

Data Index: 457038 (C4 (Web Text))

Max Activating Token Index: 196

Text #10

Max Range: 1.6111. Min Range: -1.6111

Max Act: 1.1766. Min Act: -0.0000

Data Index: 1076698 (C4 (Web Text))

Max Activating Token Index: 205

Text #11

Max Range: 1.6111. Min Range: -1.6111

Max Act: 1.2068. Min Act: -0.0000

Data Index: 741091 (C4 (Web Text))

Max Activating Token Index: 129

Text #12

Max Range: 1.6111. Min Range: -1.6111

Max Act: 1.1798. Min Act: -0.0000

Data Index: 186674 (C4 (Web Text))

Max Activating Token Index: 902

Text #13

Max Range: 1.6111. Min Range: -1.6111

Max Act: 1.1448. Min Act: -0.0000

Data Index: 472006 (C4 (Web Text))

Max Activating Token Index: 1012

Text #14

Max Range: 1.6111. Min Range: -1.6111

Max Act: 1.1556. Min Act: -0.0000

Data Index: 98802 (C4 (Web Text))

Max Activating Token Index: 460

Text #15

Max Range: 1.6111. Min Range: -1.6111

Max Act: 1.1286. Min Act: -0.0000

Data Index: 721220 (C4 (Web Text))

Max Activating Token Index: 486

Text #16

Max Range: 1.6111. Min Range: -1.6111

Max Act: 1.1048. Min Act: -0.0000

Data Index: 1142033 (C4 (Web Text))

Max Activating Token Index: 571

Text #17

Max Range: 1.6111. Min Range: -1.6111

Max Act: 1.0718. Min Act: 0.0000

Data Index: 1285223 (C4 (Web Text))

Max Activating Token Index: 919

Text #18

Max Range: 1.6111. Min Range: -1.6111

Max Act: 1.0720. Min Act: -0.0000

Data Index: 1122037 (C4 (Web Text))

Max Activating Token Index: 317

Text #19

Max Range: 1.6111. Min Range: -1.6111

Max Act: 1.0579. Min Act: -0.0000

Data Index: 876339 (C4 (Web Text))

Max Activating Token Index: 195