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

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

Neuron 351 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.3638. Min Range: -2.3638

Max Act: 2.3496. Min Act: -0.0000

Data Index: 460385 (C4 (Web Text))

Max Activating Token Index: 520

Text #1

Max Range: 2.3638. Min Range: -2.3638

Max Act: 2.3638. Min Act: -0.0000

Data Index: 176808 (C4 (Web Text))

Max Activating Token Index: 724

Text #2

Max Range: 2.3638. Min Range: -2.3638

Max Act: 2.2763. Min Act: -0.0000

Data Index: 249931 (C4 (Web Text))

Max Activating Token Index: 945

Text #3

Max Range: 2.3638. Min Range: -2.3638

Max Act: 2.1765. Min Act: -0.0000

Data Index: 661855 (C4 (Web Text))

Max Activating Token Index: 452

Text #4

Max Range: 2.3638. Min Range: -2.3638

Max Act: 2.1381. Min Act: -0.0000

Data Index: 878608 (C4 (Web Text))

Max Activating Token Index: 334

Text #5

Max Range: 2.3638. Min Range: -2.3638

Max Act: 1.8890. Min Act: -0.0000

Data Index: 1274807 (C4 (Web Text))

Max Activating Token Index: 230

Text #6

Max Range: 2.3638. Min Range: -2.3638

Max Act: 1.9826. Min Act: -0.0000

Data Index: 1132042 (C4 (Web Text))

Max Activating Token Index: 645

Text #7

Max Range: 2.3638. Min Range: -2.3638

Max Act: 2.2011. Min Act: -0.0000

Data Index: 969468 (C4 (Web Text))

Max Activating Token Index: 919

Text #8

Max Range: 2.3638. Min Range: -2.3638

Max Act: 2.0769. Min Act: -0.0000

Data Index: 325633 (C4 (Web Text))

Max Activating Token Index: 182

Text #9

Max Range: 2.3638. Min Range: -2.3638

Max Act: 2.0754. Min Act: -0.0000

Data Index: 41193 (C4 (Web Text))

Max Activating Token Index: 878

Text #10

Max Range: 2.3638. Min Range: -2.3638

Max Act: 2.1747. Min Act: -0.0000

Data Index: 511150 (C4 (Web Text))

Max Activating Token Index: 966

Text #11

Max Range: 2.3638. Min Range: -2.3638

Max Act: 1.9344. Min Act: -0.0000

Data Index: 166703 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 2.3638. Min Range: -2.3638

Max Act: 1.8297. Min Act: -0.0000

Data Index: 1243434 (C4 (Web Text))

Max Activating Token Index: 107

Text #13

Max Range: 2.3638. Min Range: -2.3638

Max Act: 1.9141. Min Act: -0.0000

Data Index: 1314052 (C4 (Web Text))

Max Activating Token Index: 187

Text #14

Max Range: 2.3638. Min Range: -2.3638

Max Act: 2.0063. Min Act: -0.0000

Data Index: 256155 (C4 (Web Text))

Max Activating Token Index: 472

Text #15

Max Range: 2.3638. Min Range: -2.3638

Max Act: 2.0188. Min Act: -0.0000

Data Index: 502168 (C4 (Web Text))

Max Activating Token Index: 333

Text #16

Max Range: 2.3638. Min Range: -2.3638

Max Act: 1.8981. Min Act: -0.0000

Data Index: 238793 (C4 (Web Text))

Max Activating Token Index: 920

Text #17

Max Range: 2.3638. Min Range: -2.3638

Max Act: 1.8623. Min Act: -0.0000

Data Index: 603753 (C4 (Web Text))

Max Activating Token Index: 471

Text #18

Max Range: 2.3638. Min Range: -2.3638

Max Act: 1.9556. Min Act: -0.0000

Data Index: 372027 (C4 (Web Text))

Max Activating Token Index: 463

Text #19

Max Range: 2.3638. Min Range: -2.3638

Max Act: 1.9556. Min Act: -0.0000

Data Index: 754427 (C4 (Web Text))

Max Activating Token Index: 924