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

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

Neuron 1794 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: 0.8885. Min Range: -0.8885

Max Act: 0.8885. Min Act: -0.0002

Data Index: 27081 (C4 (Web Text))

Max Activating Token Index: 387

Text #1

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.7478. Min Act: -0.0002

Data Index: 498636 (C4 (Web Text))

Max Activating Token Index: 485

Text #2

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.7588. Min Act: -0.0002

Data Index: 996823 (C4 (Web Text))

Max Activating Token Index: 380

Text #3

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.7538. Min Act: -0.0002

Data Index: 203270 (C4 (Web Text))

Max Activating Token Index: 861

Text #4

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.6809. Min Act: -0.0002

Data Index: 86076 (C4 (Web Text))

Max Activating Token Index: 730

Text #5

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.6428. Min Act: -0.0002

Data Index: 1100475 (C4 (Web Text))

Max Activating Token Index: 697

Text #6

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.6756. Min Act: -0.0002

Data Index: 404582 (C4 (Web Text))

Max Activating Token Index: 623

Text #7

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.6518. Min Act: -0.0002

Data Index: 133215 (C4 (Web Text))

Max Activating Token Index: 728

Text #8

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.6417. Min Act: -0.0002

Data Index: 477824 (C4 (Web Text))

Max Activating Token Index: 494

Text #9

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.6417. Min Act: -0.0002

Data Index: 412673 (C4 (Web Text))

Max Activating Token Index: 616

Text #10

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.6157. Min Act: -0.0002

Data Index: 887601 (C4 (Web Text))

Max Activating Token Index: 201

Text #11

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.6286. Min Act: -0.0002

Data Index: 759693 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.6459. Min Act: -0.0002

Data Index: 1043774 (C4 (Web Text))

Max Activating Token Index: 365

Text #13

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.6203. Min Act: -0.0002

Data Index: 31632 (C4 (Web Text))

Max Activating Token Index: 68

Text #14

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.6572. Min Act: -0.0002

Data Index: 993308 (C4 (Web Text))

Max Activating Token Index: 744

Text #15

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.6120. Min Act: -0.0002

Data Index: 781582 (C4 (Web Text))

Max Activating Token Index: 602

Text #16

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.6285. Min Act: -0.0002

Data Index: 793435 (C4 (Web Text))

Max Activating Token Index: 587

Text #17

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.5840. Min Act: -0.0002

Data Index: 1321430 (C4 (Web Text))

Max Activating Token Index: 1022

Text #18

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.6193. Min Act: -0.0002

Data Index: 79058 (C4 (Web Text))

Max Activating Token Index: 804

Text #19

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.6001. Min Act: -0.0002

Data Index: 1290117 (C4 (Web Text))

Max Activating Token Index: 744