Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 372 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0470. Min Act: -0.0003

Data Index: 1081959 (C4 (Web Text))

Max Activating Token Index: 253

Text #1

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0456. Min Act: -0.0003

Data Index: 110380 (C4 (Web Text))

Max Activating Token Index: 96

Text #2

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0453. Min Act: -0.0003

Data Index: 246690 (C4 (Web Text))

Max Activating Token Index: 1008

Text #3

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0445. Min Act: -0.0003

Data Index: 228629 (C4 (Web Text))

Max Activating Token Index: 80

Text #4

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0447. Min Act: -0.0003

Data Index: 153532 (C4 (Web Text))

Max Activating Token Index: 716

Text #5

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0431. Min Act: -0.0003

Data Index: 728280 (C4 (Web Text))

Max Activating Token Index: 99

Text #6

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0427. Min Act: -0.0004

Data Index: 395102 (C4 (Web Text))

Max Activating Token Index: 38

Text #7

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0427. Min Act: -0.0003

Data Index: 1117549 (C4 (Web Text))

Max Activating Token Index: 558

Text #8

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0429. Min Act: -0.0003

Data Index: 387015 (C4 (Web Text))

Max Activating Token Index: 331

Text #9

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0407. Min Act: -0.0003

Data Index: 3680 (C4 (Web Text))

Max Activating Token Index: 95

Text #10

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0411. Min Act: -0.0003

Data Index: 206064 (C4 (Web Text))

Max Activating Token Index: 948

Text #11

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0421. Min Act: -0.0003

Data Index: 869655 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0410. Min Act: -0.0003

Data Index: 829420 (C4 (Web Text))

Max Activating Token Index: 955

Text #13

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0421. Min Act: -0.0003

Data Index: 1081029 (C4 (Web Text))

Max Activating Token Index: 719

Text #14

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0414. Min Act: -0.0002

Data Index: 483413 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0429. Min Act: -0.0003

Data Index: 980011 (C4 (Web Text))

Max Activating Token Index: 91

Text #16

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0394. Min Act: -0.0003

Data Index: 616166 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0408. Min Act: -0.0003

Data Index: 1220262 (C4 (Web Text))

Max Activating Token Index: 1005

Text #18

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0374. Min Act: -0.0003

Data Index: 1044831 (C4 (Web Text))

Max Activating Token Index: 809

Text #19

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0405. Min Act: -0.0003

Data Index: 148203 (C4 (Web Text))

Max Activating Token Index: 222