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

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

Neuron 498 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8239. Min Range: -2.8239

Max Act: 2.8239. Min Act: -0.0000

Data Index: 1284082 (C4 (Web Text))

Max Activating Token Index: 541

Text #1

Max Range: 2.8239. Min Range: -2.8239

Max Act: 2.5816. Min Act: -0.0000

Data Index: 868149 (C4 (Web Text))

Max Activating Token Index: 97

Text #2

Max Range: 2.8239. Min Range: -2.8239

Max Act: 2.4549. Min Act: -0.0000

Data Index: 447422 (C4 (Web Text))

Max Activating Token Index: 959

Text #3

Max Range: 2.8239. Min Range: -2.8239

Max Act: 2.7072. Min Act: -0.0000

Data Index: 47072 (C4 (Web Text))

Max Activating Token Index: 928

Text #4

Max Range: 2.8239. Min Range: -2.8239

Max Act: 2.3061. Min Act: -0.0000

Data Index: 1232472 (C4 (Web Text))

Max Activating Token Index: 233

Text #5

Max Range: 2.8239. Min Range: -2.8239

Max Act: 2.3693. Min Act: -0.0000

Data Index: 303738 (C4 (Web Text))

Max Activating Token Index: 842

Text #6

Max Range: 2.8239. Min Range: -2.8239

Max Act: 2.1151. Min Act: -0.0000

Data Index: 36921 (C4 (Web Text))

Max Activating Token Index: 784

Text #7

Max Range: 2.8239. Min Range: -2.8239

Max Act: 2.2067. Min Act: -0.0000

Data Index: 104246 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 2.8239. Min Range: -2.8239

Max Act: 2.3241. Min Act: -0.0001

Data Index: 211380 (C4 (Web Text))

Max Activating Token Index: 886

Text #9

Max Range: 2.8239. Min Range: -2.8239

Max Act: 2.2546. Min Act: -0.0001

Data Index: 1330750 (C4 (Web Text))

Max Activating Token Index: 25

Text #10

Max Range: 2.8239. Min Range: -2.8239

Max Act: 2.1152. Min Act: -0.0000

Data Index: 143294 (C4 (Web Text))

Max Activating Token Index: 93

Text #11

Max Range: 2.8239. Min Range: -2.8239

Max Act: 2.3651. Min Act: -0.0000

Data Index: 1137519 (C4 (Web Text))

Max Activating Token Index: 906

Text #12

Max Range: 2.8239. Min Range: -2.8239

Max Act: 2.3370. Min Act: -0.0000

Data Index: 211627 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 2.8239. Min Range: -2.8239

Max Act: 2.0257. Min Act: -0.0001

Data Index: 1307321 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 2.8239. Min Range: -2.8239

Max Act: 2.2151. Min Act: -0.0000

Data Index: 1125780 (C4 (Web Text))

Max Activating Token Index: 404

Text #15

Max Range: 2.8239. Min Range: -2.8239

Max Act: 2.1877. Min Act: -0.0000

Data Index: 797161 (C4 (Web Text))

Max Activating Token Index: 97

Text #16

Max Range: 2.8239. Min Range: -2.8239

Max Act: 2.1838. Min Act: -0.0001

Data Index: 50947 (C4 (Web Text))

Max Activating Token Index: 826

Text #17

Max Range: 2.8239. Min Range: -2.8239

Max Act: 2.1764. Min Act: -0.0001

Data Index: 43874 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 2.8239. Min Range: -2.8239

Max Act: 2.4838. Min Act: -0.0000

Data Index: 930674 (C4 (Web Text))

Max Activating Token Index: 738

Text #19

Max Range: 2.8239. Min Range: -2.8239

Max Act: 1.8631. Min Act: -0.0001

Data Index: 1190377 (C4 (Web Text))

Max Activating Token Index: 373