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

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

Neuron 3341 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4409. Min Range: -3.4409

Max Act: 3.4409. Min Act: -0.0000

Data Index: 225606 (C4 (Web Text))

Max Activating Token Index: 41

Text #1

Max Range: 3.4409. Min Range: -3.4409

Max Act: 3.2987. Min Act: -0.0001

Data Index: 1264010 (C4 (Web Text))

Max Activating Token Index: 57

Text #2

Max Range: 3.4409. Min Range: -3.4409

Max Act: 3.2131. Min Act: -0.0000

Data Index: 1078100 (C4 (Web Text))

Max Activating Token Index: 133

Text #3

Max Range: 3.4409. Min Range: -3.4409

Max Act: 3.1984. Min Act: -0.0000

Data Index: 406358 (C4 (Web Text))

Max Activating Token Index: 184

Text #4

Max Range: 3.4409. Min Range: -3.4409

Max Act: 3.1764. Min Act: -0.0000

Data Index: 778690 (C4 (Web Text))

Max Activating Token Index: 333

Text #5

Max Range: 3.4409. Min Range: -3.4409

Max Act: 3.2949. Min Act: -0.0000

Data Index: 681207 (C4 (Web Text))

Max Activating Token Index: 213

Text #6

Max Range: 3.4409. Min Range: -3.4409

Max Act: 3.1389. Min Act: -0.0000

Data Index: 856255 (C4 (Web Text))

Max Activating Token Index: 980

Text #7

Max Range: 3.4409. Min Range: -3.4409

Max Act: 3.1161. Min Act: -0.0000

Data Index: 1182003 (C4 (Web Text))

Max Activating Token Index: 992

Text #8

Max Range: 3.4409. Min Range: -3.4409

Max Act: 3.1088. Min Act: -0.0000

Data Index: 827066 (C4 (Web Text))

Max Activating Token Index: 377

Text #9

Max Range: 3.4409. Min Range: -3.4409

Max Act: 3.0631. Min Act: -0.0000

Data Index: 738654 (C4 (Web Text))

Max Activating Token Index: 399

Text #10

Max Range: 3.4409. Min Range: -3.4409

Max Act: 3.0652. Min Act: -0.0000

Data Index: 1357688 (C4 (Web Text))

Max Activating Token Index: 804

Text #11

Max Range: 3.4409. Min Range: -3.4409

Max Act: 3.0501. Min Act: -0.0000

Data Index: 352882 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 3.4409. Min Range: -3.4409

Max Act: 3.1931. Min Act: -0.0000

Data Index: 1330797 (C4 (Web Text))

Max Activating Token Index: 694

Text #13

Max Range: 3.4409. Min Range: -3.4409

Max Act: 3.0695. Min Act: -0.0000

Data Index: 1273793 (C4 (Web Text))

Max Activating Token Index: 225

Text #14

Max Range: 3.4409. Min Range: -3.4409

Max Act: 3.0512. Min Act: -0.0000

Data Index: 954077 (C4 (Web Text))

Max Activating Token Index: 609

Text #15

Max Range: 3.4409. Min Range: -3.4409

Max Act: 3.0650. Min Act: -0.0000

Data Index: 684130 (C4 (Web Text))

Max Activating Token Index: 82

Text #16

Max Range: 3.4409. Min Range: -3.4409

Max Act: 3.0614. Min Act: -0.0000

Data Index: 1251798 (C4 (Web Text))

Max Activating Token Index: 891

Text #17

Max Range: 3.4409. Min Range: -3.4409

Max Act: 3.0141. Min Act: -0.0000

Data Index: 905446 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 3.4409. Min Range: -3.4409

Max Act: 3.0396. Min Act: -0.0000

Data Index: 452538 (C4 (Web Text))

Max Activating Token Index: 779

Text #19

Max Range: 3.4409. Min Range: -3.4409

Max Act: 3.1421. Min Act: -0.0000

Data Index: 567428 (C4 (Web Text))

Max Activating Token Index: 51