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

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

Neuron 3277 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7689. Min Range: -1.7689

Max Act: 1.7689. Min Act: -0.0001

Data Index: 1159748 (C4 (Web Text))

Max Activating Token Index: 614

Text #1

Max Range: 1.7689. Min Range: -1.7689

Max Act: 1.5851. Min Act: -0.0001

Data Index: 965453 (C4 (Web Text))

Max Activating Token Index: 394

Text #2

Max Range: 1.7689. Min Range: -1.7689

Max Act: 1.4749. Min Act: -0.0001

Data Index: 598366 (C4 (Web Text))

Max Activating Token Index: 433

Text #3

Max Range: 1.7689. Min Range: -1.7689

Max Act: 1.2782. Min Act: -0.0001

Data Index: 612447 (C4 (Web Text))

Max Activating Token Index: 650

Text #4

Max Range: 1.7689. Min Range: -1.7689

Max Act: 1.3656. Min Act: -0.0001

Data Index: 281140 (C4 (Web Text))

Max Activating Token Index: 809

Text #5

Max Range: 1.7689. Min Range: -1.7689

Max Act: 1.2759. Min Act: -0.0001

Data Index: 73909 (C4 (Web Text))

Max Activating Token Index: 539

Text #6

Max Range: 1.7689. Min Range: -1.7689

Max Act: 1.4890. Min Act: -0.0001

Data Index: 735808 (C4 (Web Text))

Max Activating Token Index: 760

Text #7

Max Range: 1.7689. Min Range: -1.7689

Max Act: 1.2864. Min Act: -0.0001

Data Index: 1083270 (C4 (Web Text))

Max Activating Token Index: 170

Text #8

Max Range: 1.7689. Min Range: -1.7689

Max Act: 0.9571. Min Act: -0.0001

Data Index: 26037 (C4 (Web Text))

Max Activating Token Index: 305

Text #9

Max Range: 1.7689. Min Range: -1.7689

Max Act: 1.1776. Min Act: -0.0001

Data Index: 1350838 (C4 (Web Text))

Max Activating Token Index: 165

Text #10

Max Range: 1.7689. Min Range: -1.7689

Max Act: 1.1671. Min Act: -0.0001

Data Index: 62914 (C4 (Web Text))

Max Activating Token Index: 371

Text #11

Max Range: 1.7689. Min Range: -1.7689

Max Act: 1.1289. Min Act: -0.0001

Data Index: 1286529 (C4 (Web Text))

Max Activating Token Index: 300

Text #12

Max Range: 1.7689. Min Range: -1.7689

Max Act: 1.1833. Min Act: -0.0001

Data Index: 1358167 (C4 (Web Text))

Max Activating Token Index: 682

Text #13

Max Range: 1.7689. Min Range: -1.7689

Max Act: 0.8905. Min Act: -0.0001

Data Index: 710683 (C4 (Web Text))

Max Activating Token Index: 103

Text #14

Max Range: 1.7689. Min Range: -1.7689

Max Act: 0.8686. Min Act: -0.0001

Data Index: 953455 (C4 (Web Text))

Max Activating Token Index: 304

Text #15

Max Range: 1.7689. Min Range: -1.7689

Max Act: 0.7609. Min Act: -0.0001

Data Index: 900242 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 1.7689. Min Range: -1.7689

Max Act: 0.9824. Min Act: -0.0001

Data Index: 1118982 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 1.7689. Min Range: -1.7689

Max Act: 0.8841. Min Act: -0.0001

Data Index: 475457 (C4 (Web Text))

Max Activating Token Index: 978

Text #18

Max Range: 1.7689. Min Range: -1.7689

Max Act: 0.9790. Min Act: -0.0001

Data Index: 229601 (C4 (Web Text))

Max Activating Token Index: 470

Text #19

Max Range: 1.7689. Min Range: -1.7689

Max Act: 1.0546. Min Act: -0.0001

Data Index: 332677 (C4 (Web Text))

Max Activating Token Index: 527