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

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

Neuron 1824 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1553. Min Act: -0.0002

Data Index: 85351 (C4 (Web Text))

Max Activating Token Index: 436

Text #1

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1421. Min Act: -0.0002

Data Index: 146550 (C4 (Web Text))

Max Activating Token Index: 161

Text #2

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1397. Min Act: -0.0002

Data Index: 387591 (C4 (Web Text))

Max Activating Token Index: 347

Text #3

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1186. Min Act: -0.0002

Data Index: 371442 (C4 (Web Text))

Max Activating Token Index: 1009

Text #4

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1217. Min Act: -0.0002

Data Index: 911882 (C4 (Web Text))

Max Activating Token Index: 125

Text #5

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1253. Min Act: -0.0002

Data Index: 643518 (C4 (Web Text))

Max Activating Token Index: 496

Text #6

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1117. Min Act: -0.0002

Data Index: 1008738 (C4 (Web Text))

Max Activating Token Index: 867

Text #7

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1050. Min Act: -0.0002

Data Index: 478237 (C4 (Web Text))

Max Activating Token Index: 72

Text #8

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1036. Min Act: -0.0002

Data Index: 621825 (C4 (Web Text))

Max Activating Token Index: 533

Text #9

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1032. Min Act: -0.0002

Data Index: 715385 (C4 (Web Text))

Max Activating Token Index: 385

Text #10

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1082. Min Act: -0.0002

Data Index: 582520 (C4 (Web Text))

Max Activating Token Index: 312

Text #11

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1032. Min Act: -0.0002

Data Index: 863676 (C4 (Web Text))

Max Activating Token Index: 211

Text #12

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0931. Min Act: -0.0002

Data Index: 772064 (C4 (Web Text))

Max Activating Token Index: 461

Text #13

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0942. Min Act: -0.0002

Data Index: 3727 (C4 (Web Text))

Max Activating Token Index: 961

Text #14

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0911. Min Act: -0.0002

Data Index: 344049 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0839. Min Act: -0.0002

Data Index: 1051140 (C4 (Web Text))

Max Activating Token Index: 583

Text #16

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0804. Min Act: -0.0002

Data Index: 824646 (C4 (Web Text))

Max Activating Token Index: 627

Text #17

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0787. Min Act: -0.0002

Data Index: 133630 (C4 (Web Text))

Max Activating Token Index: 609

Text #18

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0778. Min Act: -0.0002

Data Index: 814601 (C4 (Web Text))

Max Activating Token Index: 803

Text #19

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0762. Min Act: -0.0002

Data Index: 247030 (C4 (Web Text))

Max Activating Token Index: 140