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

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

Neuron 1831 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3329. Min Range: -4.3329

Max Act: 4.3329. Min Act: -0.0000

Data Index: 324772 (C4 (Web Text))

Max Activating Token Index: 908

Text #1

Max Range: 4.3329. Min Range: -4.3329

Max Act: 3.8353. Min Act: -0.0000

Data Index: 1046626 (C4 (Web Text))

Max Activating Token Index: 162

Text #2

Max Range: 4.3329. Min Range: -4.3329

Max Act: 3.3901. Min Act: -0.0000

Data Index: 62590 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 4.3329. Min Range: -4.3329

Max Act: 3.4726. Min Act: -0.0000

Data Index: 885612 (C4 (Web Text))

Max Activating Token Index: 567

Text #4

Max Range: 4.3329. Min Range: -4.3329

Max Act: 2.8943. Min Act: -0.0000

Data Index: 1685 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 4.3329. Min Range: -4.3329

Max Act: 3.0078. Min Act: -0.0000

Data Index: 1108130 (C4 (Web Text))

Max Activating Token Index: 772

Text #6

Max Range: 4.3329. Min Range: -4.3329

Max Act: 2.7919. Min Act: -0.0000

Data Index: 869611 (C4 (Web Text))

Max Activating Token Index: 598

Text #7

Max Range: 4.3329. Min Range: -4.3329

Max Act: 2.4411. Min Act: -0.0000

Data Index: 562945 (C4 (Web Text))

Max Activating Token Index: 745

Text #8

Max Range: 4.3329. Min Range: -4.3329

Max Act: 2.5837. Min Act: -0.0000

Data Index: 200883 (C4 (Web Text))

Max Activating Token Index: 179

Text #9

Max Range: 4.3329. Min Range: -4.3329

Max Act: 2.5764. Min Act: -0.0000

Data Index: 1001941 (C4 (Web Text))

Max Activating Token Index: 898

Text #10

Max Range: 4.3329. Min Range: -4.3329

Max Act: 2.5517. Min Act: -0.0000

Data Index: 420060 (C4 (Web Text))

Max Activating Token Index: 87

Text #11

Max Range: 4.3329. Min Range: -4.3329

Max Act: 2.5378. Min Act: -0.0000

Data Index: 689664 (C4 (Web Text))

Max Activating Token Index: 900

Text #12

Max Range: 4.3329. Min Range: -4.3329

Max Act: 2.3963. Min Act: -0.0000

Data Index: 719305 (C4 (Web Text))

Max Activating Token Index: 930

Text #13

Max Range: 4.3329. Min Range: -4.3329

Max Act: 2.5101. Min Act: -0.0000

Data Index: 904079 (C4 (Web Text))

Max Activating Token Index: 441

Text #14

Max Range: 4.3329. Min Range: -4.3329

Max Act: 2.6376. Min Act: -0.0000

Data Index: 346056 (C4 (Web Text))

Max Activating Token Index: 77

Text #15

Max Range: 4.3329. Min Range: -4.3329

Max Act: 2.7779. Min Act: -0.0000

Data Index: 270640 (C4 (Web Text))

Max Activating Token Index: 96

Text #16

Max Range: 4.3329. Min Range: -4.3329

Max Act: 2.6149. Min Act: -0.0000

Data Index: 1091148 (C4 (Web Text))

Max Activating Token Index: 676

Text #17

Max Range: 4.3329. Min Range: -4.3329

Max Act: 2.6256. Min Act: -0.0000

Data Index: 243256 (C4 (Web Text))

Max Activating Token Index: 543

Text #18

Max Range: 4.3329. Min Range: -4.3329

Max Act: 2.7472. Min Act: -0.0000

Data Index: 671763 (C4 (Web Text))

Max Activating Token Index: 43

Text #19

Max Range: 4.3329. Min Range: -4.3329

Max Act: 2.4946. Min Act: -0.0000

Data Index: 887577 (C4 (Web Text))

Max Activating Token Index: 932