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

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

Neuron 2352 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8399. Min Range: -2.8399

Max Act: 2.7940. Min Act: -0.0000

Data Index: 1351645 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 2.8399. Min Range: -2.8399

Max Act: 2.8399. Min Act: -0.0000

Data Index: 166990 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 2.8399. Min Range: -2.8399

Max Act: 2.6605. Min Act: -0.0000

Data Index: 628313 (C4 (Web Text))

Max Activating Token Index: 13

Text #3

Max Range: 2.8399. Min Range: -2.8399

Max Act: 2.4922. Min Act: -0.0000

Data Index: 1186479 (C4 (Web Text))

Max Activating Token Index: 27

Text #4

Max Range: 2.8399. Min Range: -2.8399

Max Act: 2.6044. Min Act: -0.0000

Data Index: 1275799 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 2.8399. Min Range: -2.8399

Max Act: 2.4642. Min Act: -0.0000

Data Index: 397176 (C4 (Web Text))

Max Activating Token Index: 29

Text #6

Max Range: 2.8399. Min Range: -2.8399

Max Act: 2.6800. Min Act: -0.0000

Data Index: 188510 (C4 (Web Text))

Max Activating Token Index: 11

Text #7

Max Range: 2.8399. Min Range: -2.8399

Max Act: 2.5250. Min Act: -0.0000

Data Index: 688966 (C4 (Web Text))

Max Activating Token Index: 11

Text #8

Max Range: 2.8399. Min Range: -2.8399

Max Act: 2.2829. Min Act: -0.0000

Data Index: 233316 (C4 (Web Text))

Max Activating Token Index: 821

Text #9

Max Range: 2.8399. Min Range: -2.8399

Max Act: 2.4148. Min Act: -0.0000

Data Index: 812883 (C4 (Web Text))

Max Activating Token Index: 725

Text #10

Max Range: 2.8399. Min Range: -2.8399

Max Act: 2.3982. Min Act: -0.0000

Data Index: 1216721 (C4 (Web Text))

Max Activating Token Index: 830

Text #11

Max Range: 2.8399. Min Range: -2.8399

Max Act: 2.1413. Min Act: -0.0000

Data Index: 290848 (C4 (Web Text))

Max Activating Token Index: 831

Text #12

Max Range: 2.8399. Min Range: -2.8399

Max Act: 2.3525. Min Act: -0.0000

Data Index: 198274 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 2.8399. Min Range: -2.8399

Max Act: 2.2159. Min Act: -0.0000

Data Index: 1215797 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 2.8399. Min Range: -2.8399

Max Act: 2.4565. Min Act: -0.0000

Data Index: 161060 (C4 (Web Text))

Max Activating Token Index: 932

Text #15

Max Range: 2.8399. Min Range: -2.8399

Max Act: 2.3313. Min Act: -0.0000

Data Index: 1244235 (C4 (Web Text))

Max Activating Token Index: 28

Text #16

Max Range: 2.8399. Min Range: -2.8399

Max Act: 2.4318. Min Act: -0.0000

Data Index: 445895 (C4 (Web Text))

Max Activating Token Index: 705

Text #17

Max Range: 2.8399. Min Range: -2.8399

Max Act: 2.0759. Min Act: -0.0000

Data Index: 286464 (C4 (Web Text))

Max Activating Token Index: 739

Text #18

Max Range: 2.8399. Min Range: -2.8399

Max Act: 2.1848. Min Act: -0.0000

Data Index: 219706 (C4 (Web Text))

Max Activating Token Index: 734

Text #19

Max Range: 2.8399. Min Range: -2.8399

Max Act: 2.1823. Min Act: -0.0000

Data Index: 388126 (C4 (Web Text))

Max Activating Token Index: 705