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

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

Neuron 1798 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.3027. Min Range: -6.3027

Max Act: 5.9945. Min Act: -0.0000

Data Index: 1014263 (C4 (Web Text))

Max Activating Token Index: 433

Text #1

Max Range: 6.3027. Min Range: -6.3027

Max Act: 6.3027. Min Act: -0.0000

Data Index: 656239 (C4 (Web Text))

Max Activating Token Index: 555

Text #2

Max Range: 6.3027. Min Range: -6.3027

Max Act: 6.0229. Min Act: -0.0000

Data Index: 786941 (C4 (Web Text))

Max Activating Token Index: 438

Text #3

Max Range: 6.3027. Min Range: -6.3027

Max Act: 6.2137. Min Act: -0.0000

Data Index: 585491 (C4 (Web Text))

Max Activating Token Index: 494

Text #4

Max Range: 6.3027. Min Range: -6.3027

Max Act: 5.8664. Min Act: -0.0000

Data Index: 515937 (C4 (Web Text))

Max Activating Token Index: 599

Text #5

Max Range: 6.3027. Min Range: -6.3027

Max Act: 5.8812. Min Act: -0.0000

Data Index: 543283 (C4 (Web Text))

Max Activating Token Index: 638

Text #6

Max Range: 6.3027. Min Range: -6.3027

Max Act: 5.7759. Min Act: -0.0000

Data Index: 600775 (C4 (Web Text))

Max Activating Token Index: 698

Text #7

Max Range: 6.3027. Min Range: -6.3027

Max Act: 5.4167. Min Act: -0.0000

Data Index: 849972 (C4 (Web Text))

Max Activating Token Index: 731

Text #8

Max Range: 6.3027. Min Range: -6.3027

Max Act: 6.0684. Min Act: -0.0000

Data Index: 1199379 (C4 (Web Text))

Max Activating Token Index: 491

Text #9

Max Range: 6.3027. Min Range: -6.3027

Max Act: 5.6929. Min Act: -0.0000

Data Index: 1015615 (C4 (Web Text))

Max Activating Token Index: 167

Text #10

Max Range: 6.3027. Min Range: -6.3027

Max Act: 5.7760. Min Act: -0.0000

Data Index: 1087145 (C4 (Web Text))

Max Activating Token Index: 488

Text #11

Max Range: 6.3027. Min Range: -6.3027

Max Act: 5.7876. Min Act: -0.0000

Data Index: 301003 (C4 (Web Text))

Max Activating Token Index: 862

Text #12

Max Range: 6.3027. Min Range: -6.3027

Max Act: 5.3627. Min Act: -0.0000

Data Index: 782441 (C4 (Web Text))

Max Activating Token Index: 819

Text #13

Max Range: 6.3027. Min Range: -6.3027

Max Act: 5.5667. Min Act: -0.0000

Data Index: 907755 (C4 (Web Text))

Max Activating Token Index: 710

Text #14

Max Range: 6.3027. Min Range: -6.3027

Max Act: 5.3951. Min Act: -0.0000

Data Index: 448178 (C4 (Web Text))

Max Activating Token Index: 639

Text #15

Max Range: 6.3027. Min Range: -6.3027

Max Act: 5.5293. Min Act: -0.0000

Data Index: 1329339 (C4 (Web Text))

Max Activating Token Index: 235

Text #16

Max Range: 6.3027. Min Range: -6.3027

Max Act: 5.4936. Min Act: -0.0000

Data Index: 927823 (C4 (Web Text))

Max Activating Token Index: 631

Text #17

Max Range: 6.3027. Min Range: -6.3027

Max Act: 5.6350. Min Act: -0.0000

Data Index: 884621 (C4 (Web Text))

Max Activating Token Index: 638

Text #18

Max Range: 6.3027. Min Range: -6.3027

Max Act: 5.8366. Min Act: -0.0000

Data Index: 175185 (C4 (Web Text))

Max Activating Token Index: 806

Text #19

Max Range: 6.3027. Min Range: -6.3027

Max Act: 5.2351. Min Act: -0.0000

Data Index: 449001 (C4 (Web Text))

Max Activating Token Index: 786