Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4750 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4865. Min Range: -1.4865

Max Act: 1.4865. Min Act: -0.0000

Data Index: 1181868 (C4 (Web Text))

Max Activating Token Index: 702

Text #1

Max Range: 1.4865. Min Range: -1.4865

Max Act: 1.3303. Min Act: -0.0000

Data Index: 23961 (C4 (Web Text))

Max Activating Token Index: 28

Text #2

Max Range: 1.4865. Min Range: -1.4865

Max Act: 1.1851. Min Act: -0.0000

Data Index: 517384 (C4 (Web Text))

Max Activating Token Index: 931

Text #3

Max Range: 1.4865. Min Range: -1.4865

Max Act: 1.3186. Min Act: -0.0000

Data Index: 627331 (C4 (Web Text))

Max Activating Token Index: 853

Text #4

Max Range: 1.4865. Min Range: -1.4865

Max Act: 1.1413. Min Act: -0.0000

Data Index: 488654 (C4 (Web Text))

Max Activating Token Index: 652

Text #5

Max Range: 1.4865. Min Range: -1.4865

Max Act: 1.1320. Min Act: -0.0000

Data Index: 603055 (C4 (Web Text))

Max Activating Token Index: 779

Text #6

Max Range: 1.4865. Min Range: -1.4865

Max Act: 1.2491. Min Act: -0.0000

Data Index: 713669 (C4 (Web Text))

Max Activating Token Index: 326

Text #7

Max Range: 1.4865. Min Range: -1.4865

Max Act: 1.1939. Min Act: -0.0000

Data Index: 598984 (C4 (Web Text))

Max Activating Token Index: 295

Text #8

Max Range: 1.4865. Min Range: -1.4865

Max Act: 1.2412. Min Act: -0.0000

Data Index: 719962 (C4 (Web Text))

Max Activating Token Index: 871

Text #9

Max Range: 1.4865. Min Range: -1.4865

Max Act: 1.1235. Min Act: -0.0000

Data Index: 45530 (C4 (Web Text))

Max Activating Token Index: 1012

Text #10

Max Range: 1.4865. Min Range: -1.4865

Max Act: 1.0171. Min Act: -0.0000

Data Index: 213167 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 1.4865. Min Range: -1.4865

Max Act: 1.0614. Min Act: -0.0000

Data Index: 575042 (C4 (Web Text))

Max Activating Token Index: 867

Text #12

Max Range: 1.4865. Min Range: -1.4865

Max Act: 1.0599. Min Act: -0.0000

Data Index: 80319 (C4 (Web Text))

Max Activating Token Index: 762

Text #13

Max Range: 1.4865. Min Range: -1.4865

Max Act: 1.0643. Min Act: -0.0000

Data Index: 980133 (C4 (Web Text))

Max Activating Token Index: 516

Text #14

Max Range: 1.4865. Min Range: -1.4865

Max Act: 1.0643. Min Act: -0.0000

Data Index: 1101149 (C4 (Web Text))

Max Activating Token Index: 68

Text #15

Max Range: 1.4865. Min Range: -1.4865

Max Act: 1.0474. Min Act: -0.0000

Data Index: 266898 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 1.4865. Min Range: -1.4865

Max Act: 1.0349. Min Act: -0.0000

Data Index: 451494 (C4 (Web Text))

Max Activating Token Index: 341

Text #17

Max Range: 1.4865. Min Range: -1.4865

Max Act: 0.9609. Min Act: -0.0000

Data Index: 774390 (C4 (Web Text))

Max Activating Token Index: 462

Text #18

Max Range: 1.4865. Min Range: -1.4865

Max Act: 1.0347. Min Act: -0.0000

Data Index: 20379 (C4 (Web Text))

Max Activating Token Index: 821

Text #19

Max Range: 1.4865. Min Range: -1.4865

Max Act: 0.9848. Min Act: -0.0000

Data Index: 956982 (C4 (Web Text))

Max Activating Token Index: 473