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

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

Neuron 511 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6137. Min Range: -2.6137

Max Act: 2.5349. Min Act: -0.0000

Data Index: 413793 (C4 (Web Text))

Max Activating Token Index: 647

Text #1

Max Range: 2.6137. Min Range: -2.6137

Max Act: 2.6137. Min Act: -0.0000

Data Index: 1026562 (C4 (Web Text))

Max Activating Token Index: 916

Text #2

Max Range: 2.6137. Min Range: -2.6137

Max Act: 2.3276. Min Act: -0.0000

Data Index: 717426 (C4 (Web Text))

Max Activating Token Index: 666

Text #3

Max Range: 2.6137. Min Range: -2.6137

Max Act: 2.1900. Min Act: -0.0000

Data Index: 1347966 (C4 (Web Text))

Max Activating Token Index: 829

Text #4

Max Range: 2.6137. Min Range: -2.6137

Max Act: 2.1638. Min Act: -0.0000

Data Index: 1326318 (C4 (Web Text))

Max Activating Token Index: 719

Text #5

Max Range: 2.6137. Min Range: -2.6137

Max Act: 2.1081. Min Act: -0.0000

Data Index: 232462 (C4 (Web Text))

Max Activating Token Index: 610

Text #6

Max Range: 2.6137. Min Range: -2.6137

Max Act: 1.9297. Min Act: -0.0000

Data Index: 1275315 (C4 (Web Text))

Max Activating Token Index: 629

Text #7

Max Range: 2.6137. Min Range: -2.6137

Max Act: 1.8429. Min Act: -0.0000

Data Index: 568108 (C4 (Web Text))

Max Activating Token Index: 816

Text #8

Max Range: 2.6137. Min Range: -2.6137

Max Act: 2.1227. Min Act: -0.0000

Data Index: 908052 (C4 (Web Text))

Max Activating Token Index: 266

Text #9

Max Range: 2.6137. Min Range: -2.6137

Max Act: 1.9386. Min Act: -0.0000

Data Index: 394054 (C4 (Web Text))

Max Activating Token Index: 887

Text #10

Max Range: 2.6137. Min Range: -2.6137

Max Act: 1.9622. Min Act: -0.0000

Data Index: 112660 (C4 (Web Text))

Max Activating Token Index: 423

Text #11

Max Range: 2.6137. Min Range: -2.6137

Max Act: 1.8720. Min Act: -0.0000

Data Index: 1229727 (C4 (Web Text))

Max Activating Token Index: 835

Text #12

Max Range: 2.6137. Min Range: -2.6137

Max Act: 1.8164. Min Act: -0.0000

Data Index: 702249 (C4 (Web Text))

Max Activating Token Index: 898

Text #13

Max Range: 2.6137. Min Range: -2.6137

Max Act: 1.9348. Min Act: -0.0000

Data Index: 449822 (C4 (Web Text))

Max Activating Token Index: 282

Text #14

Max Range: 2.6137. Min Range: -2.6137

Max Act: 1.6628. Min Act: -0.0000

Data Index: 1202044 (C4 (Web Text))

Max Activating Token Index: 424

Text #15

Max Range: 2.6137. Min Range: -2.6137

Max Act: 1.8913. Min Act: -0.0000

Data Index: 632376 (C4 (Web Text))

Max Activating Token Index: 452

Text #16

Max Range: 2.6137. Min Range: -2.6137

Max Act: 1.7705. Min Act: -0.0000

Data Index: 1316446 (C4 (Web Text))

Max Activating Token Index: 263

Text #17

Max Range: 2.6137. Min Range: -2.6137

Max Act: 1.7360. Min Act: -0.0000

Data Index: 294105 (C4 (Web Text))

Max Activating Token Index: 577

Text #18

Max Range: 2.6137. Min Range: -2.6137

Max Act: 1.6558. Min Act: -0.0000

Data Index: 1285822 (C4 (Web Text))

Max Activating Token Index: 808

Text #19

Max Range: 2.6137. Min Range: -2.6137

Max Act: 1.6216. Min Act: -0.0000

Data Index: 794501 (C4 (Web Text))

Max Activating Token Index: 685