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

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

Neuron 3597 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: 0.2140. Min Range: -0.2140

Max Act: 0.1729. Min Act: -0.0002

Data Index: 732453 (C4 (Web Text))

Max Activating Token Index: 264

Text #1

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.2036. Min Act: -0.0002

Data Index: 894882 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.2140. Min Act: -0.0002

Data Index: 366285 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.1804. Min Act: -0.0002

Data Index: 371611 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.1709. Min Act: -0.0002

Data Index: 833433 (C4 (Web Text))

Max Activating Token Index: 353

Text #5

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.1893. Min Act: -0.0002

Data Index: 1322784 (C4 (Web Text))

Max Activating Token Index: 872

Text #6

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.1762. Min Act: -0.0002

Data Index: 1015486 (C4 (Web Text))

Max Activating Token Index: 9

Text #7

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.1857. Min Act: -0.0002

Data Index: 648282 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.1821. Min Act: -0.0002

Data Index: 914021 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.1876. Min Act: -0.0002

Data Index: 460595 (C4 (Web Text))

Max Activating Token Index: 435

Text #10

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.1921. Min Act: -0.0002

Data Index: 137127 (C4 (Web Text))

Max Activating Token Index: 745

Text #11

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.1780. Min Act: -0.0002

Data Index: 1186543 (C4 (Web Text))

Max Activating Token Index: 161

Text #12

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.1668. Min Act: -0.0002

Data Index: 484113 (C4 (Web Text))

Max Activating Token Index: 806

Text #13

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.1407. Min Act: -0.0002

Data Index: 244290 (C4 (Web Text))

Max Activating Token Index: 942

Text #14

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.1799. Min Act: -0.0002

Data Index: 343255 (C4 (Web Text))

Max Activating Token Index: 201

Text #15

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.1833. Min Act: -0.0002

Data Index: 681767 (C4 (Web Text))

Max Activating Token Index: 1010

Text #16

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.1731. Min Act: -0.0002

Data Index: 1267676 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.2020. Min Act: -0.0002

Data Index: 30300 (C4 (Web Text))

Max Activating Token Index: 769

Text #18

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.1469. Min Act: -0.0002

Data Index: 1284614 (C4 (Web Text))

Max Activating Token Index: 601

Text #19

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.1650. Min Act: -0.0002

Data Index: 1025798 (C4 (Web Text))

Max Activating Token Index: 488