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

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

Neuron 1565 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: 0.2296. Min Range: -0.2296

Max Act: 0.2296. Min Act: -0.0002

Data Index: 418706 (C4 (Web Text))

Max Activating Token Index: 511

Text #1

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.2053. Min Act: -0.0002

Data Index: 65647 (C4 (Web Text))

Max Activating Token Index: 61

Text #2

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1932. Min Act: -0.0002

Data Index: 683063 (C4 (Web Text))

Max Activating Token Index: 114

Text #3

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1911. Min Act: -0.0002

Data Index: 1044018 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1949. Min Act: -0.0002

Data Index: 773947 (C4 (Web Text))

Max Activating Token Index: 191

Text #5

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1852. Min Act: -0.0002

Data Index: 458769 (C4 (Web Text))

Max Activating Token Index: 722

Text #6

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1784. Min Act: -0.0002

Data Index: 393121 (C4 (Web Text))

Max Activating Token Index: 360

Text #7

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1951. Min Act: -0.0002

Data Index: 1286303 (C4 (Web Text))

Max Activating Token Index: 110

Text #8

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1785. Min Act: -0.0002

Data Index: 600363 (C4 (Web Text))

Max Activating Token Index: 557

Text #9

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1673. Min Act: -0.0002

Data Index: 8825 (C4 (Web Text))

Max Activating Token Index: 674

Text #10

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1995. Min Act: -0.0002

Data Index: 354334 (C4 (Web Text))

Max Activating Token Index: 188

Text #11

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1903. Min Act: -0.0002

Data Index: 1184379 (C4 (Web Text))

Max Activating Token Index: 330

Text #12

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1797. Min Act: -0.0002

Data Index: 403652 (C4 (Web Text))

Max Activating Token Index: 279

Text #13

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1812. Min Act: -0.0002

Data Index: 672125 (C4 (Web Text))

Max Activating Token Index: 327

Text #14

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1737. Min Act: -0.0002

Data Index: 1336555 (C4 (Web Text))

Max Activating Token Index: 510

Text #15

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.2027. Min Act: -0.0002

Data Index: 400447 (C4 (Web Text))

Max Activating Token Index: 669

Text #16

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1886. Min Act: -0.0002

Data Index: 377649 (C4 (Web Text))

Max Activating Token Index: 265

Text #17

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1693. Min Act: -0.0002

Data Index: 501536 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1813. Min Act: -0.0002

Data Index: 364912 (C4 (Web Text))

Max Activating Token Index: 21

Text #19

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1657. Min Act: -0.0002

Data Index: 1170943 (C4 (Web Text))

Max Activating Token Index: 33