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

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

Neuron 5433 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0374. Min Range: -1.0374

Max Act: 1.0374. Min Act: -0.0000

Data Index: 656238 (C4 (Web Text))

Max Activating Token Index: 375

Text #1

Max Range: 1.0374. Min Range: -1.0374

Max Act: 0.9559. Min Act: -0.0000

Data Index: 312978 (C4 (Web Text))

Max Activating Token Index: 960

Text #2

Max Range: 1.0374. Min Range: -1.0374

Max Act: 0.8811. Min Act: -0.0000

Data Index: 1061217 (C4 (Web Text))

Max Activating Token Index: 819

Text #3

Max Range: 1.0374. Min Range: -1.0374

Max Act: 0.8800. Min Act: -0.0000

Data Index: 431260 (C4 (Web Text))

Max Activating Token Index: 498

Text #4

Max Range: 1.0374. Min Range: -1.0374

Max Act: 0.8301. Min Act: -0.0000

Data Index: 745919 (C4 (Web Text))

Max Activating Token Index: 734

Text #5

Max Range: 1.0374. Min Range: -1.0374

Max Act: 0.7893. Min Act: 0.0000

Data Index: 1019623 (C4 (Web Text))

Max Activating Token Index: 684

Text #6

Max Range: 1.0374. Min Range: -1.0374

Max Act: 0.7270. Min Act: -0.0000

Data Index: 1198893 (C4 (Web Text))

Max Activating Token Index: 379

Text #7

Max Range: 1.0374. Min Range: -1.0374

Max Act: 0.7076. Min Act: -0.0000

Data Index: 513326 (C4 (Web Text))

Max Activating Token Index: 393

Text #8

Max Range: 1.0374. Min Range: -1.0374

Max Act: 0.6886. Min Act: -0.0000

Data Index: 941066 (C4 (Web Text))

Max Activating Token Index: 98

Text #9

Max Range: 1.0374. Min Range: -1.0374

Max Act: 0.6908. Min Act: -0.0000

Data Index: 222341 (C4 (Web Text))

Max Activating Token Index: 601

Text #10

Max Range: 1.0374. Min Range: -1.0374

Max Act: 0.6610. Min Act: -0.0000

Data Index: 827189 (C4 (Web Text))

Max Activating Token Index: 630

Text #11

Max Range: 1.0374. Min Range: -1.0374

Max Act: 0.6409. Min Act: -0.0000

Data Index: 822130 (C4 (Web Text))

Max Activating Token Index: 130

Text #12

Max Range: 1.0374. Min Range: -1.0374

Max Act: 0.7216. Min Act: -0.0000

Data Index: 166635 (C4 (Web Text))

Max Activating Token Index: 130

Text #13

Max Range: 1.0374. Min Range: -1.0374

Max Act: 0.6969. Min Act: -0.0000

Data Index: 1144740 (C4 (Web Text))

Max Activating Token Index: 888

Text #14

Max Range: 1.0374. Min Range: -1.0374

Max Act: 0.6696. Min Act: -0.0000

Data Index: 660087 (C4 (Web Text))

Max Activating Token Index: 561

Text #15

Max Range: 1.0374. Min Range: -1.0374

Max Act: 0.7012. Min Act: -0.0000

Data Index: 1046571 (C4 (Web Text))

Max Activating Token Index: 592

Text #16

Max Range: 1.0374. Min Range: -1.0374

Max Act: 0.6275. Min Act: -0.0000

Data Index: 1472215 (Python Code)

Max Activating Token Index: 120

Text #17

Max Range: 1.0374. Min Range: -1.0374

Max Act: 0.6320. Min Act: -0.0000

Data Index: 565307 (C4 (Web Text))

Max Activating Token Index: 908

Text #18

Max Range: 1.0374. Min Range: -1.0374

Max Act: 0.6531. Min Act: -0.0000

Data Index: 1345334 (C4 (Web Text))

Max Activating Token Index: 194

Text #19

Max Range: 1.0374. Min Range: -1.0374

Max Act: 0.6525. Min Act: -0.0000

Data Index: 565718 (C4 (Web Text))

Max Activating Token Index: 647