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

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

Neuron 3284 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: 1.2187. Min Range: -1.2187

Max Act: 1.2187. Min Act: -0.0002

Data Index: 859370 (C4 (Web Text))

Max Activating Token Index: 319

Text #1

Max Range: 1.2187. Min Range: -1.2187

Max Act: 1.0776. Min Act: -0.0002

Data Index: 91506 (C4 (Web Text))

Max Activating Token Index: 883

Text #2

Max Range: 1.2187. Min Range: -1.2187

Max Act: 1.0786. Min Act: -0.0002

Data Index: 1179955 (C4 (Web Text))

Max Activating Token Index: 556

Text #3

Max Range: 1.2187. Min Range: -1.2187

Max Act: 0.9632. Min Act: -0.0002

Data Index: 908068 (C4 (Web Text))

Max Activating Token Index: 723

Text #4

Max Range: 1.2187. Min Range: -1.2187

Max Act: 1.0211. Min Act: -0.0002

Data Index: 1187969 (C4 (Web Text))

Max Activating Token Index: 897

Text #5

Max Range: 1.2187. Min Range: -1.2187

Max Act: 0.9037. Min Act: -0.0002

Data Index: 382647 (C4 (Web Text))

Max Activating Token Index: 147

Text #6

Max Range: 1.2187. Min Range: -1.2187

Max Act: 0.9773. Min Act: -0.0002

Data Index: 1044395 (C4 (Web Text))

Max Activating Token Index: 377

Text #7

Max Range: 1.2187. Min Range: -1.2187

Max Act: 1.0471. Min Act: -0.0002

Data Index: 625430 (C4 (Web Text))

Max Activating Token Index: 999

Text #8

Max Range: 1.2187. Min Range: -1.2187

Max Act: 0.9910. Min Act: -0.0002

Data Index: 679466 (C4 (Web Text))

Max Activating Token Index: 551

Text #9

Max Range: 1.2187. Min Range: -1.2187

Max Act: 0.9167. Min Act: -0.0002

Data Index: 1078749 (C4 (Web Text))

Max Activating Token Index: 330

Text #10

Max Range: 1.2187. Min Range: -1.2187

Max Act: 0.9867. Min Act: -0.0002

Data Index: 832304 (C4 (Web Text))

Max Activating Token Index: 356

Text #11

Max Range: 1.2187. Min Range: -1.2187

Max Act: 1.0479. Min Act: -0.0002

Data Index: 154615 (C4 (Web Text))

Max Activating Token Index: 194

Text #12

Max Range: 1.2187. Min Range: -1.2187

Max Act: 0.9469. Min Act: -0.0002

Data Index: 1184876 (C4 (Web Text))

Max Activating Token Index: 241

Text #13

Max Range: 1.2187. Min Range: -1.2187

Max Act: 0.9890. Min Act: -0.0002

Data Index: 897660 (C4 (Web Text))

Max Activating Token Index: 61

Text #14

Max Range: 1.2187. Min Range: -1.2187

Max Act: 0.9870. Min Act: -0.0002

Data Index: 495336 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 1.2187. Min Range: -1.2187

Max Act: 0.9211. Min Act: -0.0002

Data Index: 455124 (C4 (Web Text))

Max Activating Token Index: 475

Text #16

Max Range: 1.2187. Min Range: -1.2187

Max Act: 0.8812. Min Act: -0.0002

Data Index: 265472 (C4 (Web Text))

Max Activating Token Index: 669

Text #17

Max Range: 1.2187. Min Range: -1.2187

Max Act: 0.8977. Min Act: -0.0002

Data Index: 595965 (C4 (Web Text))

Max Activating Token Index: 469

Text #18

Max Range: 1.2187. Min Range: -1.2187

Max Act: 0.8507. Min Act: -0.0002

Data Index: 1316850 (C4 (Web Text))

Max Activating Token Index: 746

Text #19

Max Range: 1.2187. Min Range: -1.2187

Max Act: 0.8077. Min Act: -0.0002

Data Index: 709628 (C4 (Web Text))

Max Activating Token Index: 857