Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2384 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6216. Min Range: -0.6216

Max Act: 0.6216. Min Act: -0.0001

Data Index: 1138645 (C4 (Web Text))

Max Activating Token Index: 93

Text #1

Max Range: 0.6216. Min Range: -0.6216

Max Act: 0.5585. Min Act: -0.0001

Data Index: 914417 (C4 (Web Text))

Max Activating Token Index: 520

Text #2

Max Range: 0.6216. Min Range: -0.6216

Max Act: 0.5296. Min Act: -0.0001

Data Index: 991875 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 0.6216. Min Range: -0.6216

Max Act: 0.5129. Min Act: -0.0001

Data Index: 262158 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 0.6216. Min Range: -0.6216

Max Act: 0.4883. Min Act: -0.0001

Data Index: 900267 (C4 (Web Text))

Max Activating Token Index: 260

Text #5

Max Range: 0.6216. Min Range: -0.6216

Max Act: 0.5292. Min Act: -0.0001

Data Index: 660462 (C4 (Web Text))

Max Activating Token Index: 114

Text #6

Max Range: 0.6216. Min Range: -0.6216

Max Act: 0.5084. Min Act: -0.0001

Data Index: 660683 (C4 (Web Text))

Max Activating Token Index: 658

Text #7

Max Range: 0.6216. Min Range: -0.6216

Max Act: 0.5057. Min Act: -0.0001

Data Index: 968494 (C4 (Web Text))

Max Activating Token Index: 922

Text #8

Max Range: 0.6216. Min Range: -0.6216

Max Act: 0.5146. Min Act: -0.0001

Data Index: 335999 (C4 (Web Text))

Max Activating Token Index: 823

Text #9

Max Range: 0.6216. Min Range: -0.6216

Max Act: 0.4883. Min Act: -0.0001

Data Index: 237921 (C4 (Web Text))

Max Activating Token Index: 833

Text #10

Max Range: 0.6216. Min Range: -0.6216

Max Act: 0.5335. Min Act: -0.0001

Data Index: 1042478 (C4 (Web Text))

Max Activating Token Index: 296

Text #11

Max Range: 0.6216. Min Range: -0.6216

Max Act: 0.5051. Min Act: -0.0001

Data Index: 992660 (C4 (Web Text))

Max Activating Token Index: 17

Text #12

Max Range: 0.6216. Min Range: -0.6216

Max Act: 0.4701. Min Act: -0.0001

Data Index: 715805 (C4 (Web Text))

Max Activating Token Index: 989

Text #13

Max Range: 0.6216. Min Range: -0.6216

Max Act: 0.4642. Min Act: -0.0001

Data Index: 988366 (C4 (Web Text))

Max Activating Token Index: 47

Text #14

Max Range: 0.6216. Min Range: -0.6216

Max Act: 0.4891. Min Act: -0.0001

Data Index: 209231 (C4 (Web Text))

Max Activating Token Index: 586

Text #15

Max Range: 0.6216. Min Range: -0.6216

Max Act: 0.4438. Min Act: -0.0001

Data Index: 257145 (C4 (Web Text))

Max Activating Token Index: 490

Text #16

Max Range: 0.6216. Min Range: -0.6216

Max Act: 0.4744. Min Act: -0.0001

Data Index: 356699 (C4 (Web Text))

Max Activating Token Index: 419

Text #17

Max Range: 0.6216. Min Range: -0.6216

Max Act: 0.4326. Min Act: -0.0001

Data Index: 272547 (C4 (Web Text))

Max Activating Token Index: 532

Text #18

Max Range: 0.6216. Min Range: -0.6216

Max Act: 0.4717. Min Act: -0.0001

Data Index: 951554 (C4 (Web Text))

Max Activating Token Index: 977

Text #19

Max Range: 0.6216. Min Range: -0.6216

Max Act: 0.4688. Min Act: -0.0001

Data Index: 22883 (C4 (Web Text))

Max Activating Token Index: 730