Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2705 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.5534. Min Act: -0.0003

Data Index: 94471 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.4463. Min Act: -0.0003

Data Index: 1195285 (C4 (Web Text))

Max Activating Token Index: 181

Text #2

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.3874. Min Act: -0.0003

Data Index: 22375 (C4 (Web Text))

Max Activating Token Index: 829

Text #3

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.4704. Min Act: -0.0003

Data Index: 532526 (C4 (Web Text))

Max Activating Token Index: 326

Text #4

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.4465. Min Act: -0.0003

Data Index: 1072073 (C4 (Web Text))

Max Activating Token Index: 52

Text #5

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.4284. Min Act: -0.0003

Data Index: 852924 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.4428. Min Act: -0.0003

Data Index: 910829 (C4 (Web Text))

Max Activating Token Index: 23

Text #7

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.4409. Min Act: -0.0003

Data Index: 1108123 (C4 (Web Text))

Max Activating Token Index: 22

Text #8

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.4697. Min Act: -0.0003

Data Index: 319342 (C4 (Web Text))

Max Activating Token Index: 585

Text #9

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.3576. Min Act: -0.0003

Data Index: 58779 (C4 (Web Text))

Max Activating Token Index: 273

Text #10

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.4554. Min Act: -0.0003

Data Index: 491701 (C4 (Web Text))

Max Activating Token Index: 455

Text #11

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.4380. Min Act: -0.0003

Data Index: 667375 (C4 (Web Text))

Max Activating Token Index: 68

Text #12

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.4381. Min Act: -0.0003

Data Index: 680158 (C4 (Web Text))

Max Activating Token Index: 11

Text #13

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.4351. Min Act: -0.0003

Data Index: 144354 (C4 (Web Text))

Max Activating Token Index: 142

Text #14

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.4340. Min Act: -0.0003

Data Index: 131200 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.4385. Min Act: -0.0003

Data Index: 89475 (C4 (Web Text))

Max Activating Token Index: 753

Text #16

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.3882. Min Act: -0.0003

Data Index: 404532 (C4 (Web Text))

Max Activating Token Index: 722

Text #17

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.4037. Min Act: -0.0003

Data Index: 1277341 (C4 (Web Text))

Max Activating Token Index: 859

Text #18

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.4284. Min Act: -0.0003

Data Index: 448181 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 0.5534. Min Range: -0.5534

Max Act: 0.4287. Min Act: -0.0003

Data Index: 1352678 (C4 (Web Text))

Max Activating Token Index: 412