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

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

Neuron 3018 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.6973. Min Act: -0.0001

Data Index: 430427 (C4 (Web Text))

Max Activating Token Index: 525

Text #1

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.6423. Min Act: -0.0001

Data Index: 789236 (C4 (Web Text))

Max Activating Token Index: 140

Text #2

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.6710. Min Act: -0.0001

Data Index: 409699 (C4 (Web Text))

Max Activating Token Index: 860

Text #3

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.6422. Min Act: -0.0001

Data Index: 1214917 (C4 (Web Text))

Max Activating Token Index: 174

Text #4

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.6532. Min Act: -0.0001

Data Index: 811164 (C4 (Web Text))

Max Activating Token Index: 477

Text #5

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.6732. Min Act: -0.0001

Data Index: 584414 (C4 (Web Text))

Max Activating Token Index: 358

Text #6

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.6628. Min Act: -0.0001

Data Index: 1170775 (C4 (Web Text))

Max Activating Token Index: 121

Text #7

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.6604. Min Act: -0.0001

Data Index: 876459 (C4 (Web Text))

Max Activating Token Index: 562

Text #8

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.5983. Min Act: -0.0001

Data Index: 1313518 (C4 (Web Text))

Max Activating Token Index: 791

Text #9

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.6190. Min Act: -0.0001

Data Index: 241124 (C4 (Web Text))

Max Activating Token Index: 992

Text #10

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.6016. Min Act: -0.0001

Data Index: 529244 (C4 (Web Text))

Max Activating Token Index: 612

Text #11

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.6679. Min Act: -0.0001

Data Index: 977185 (C4 (Web Text))

Max Activating Token Index: 1003

Text #12

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.6122. Min Act: -0.0001

Data Index: 138662 (C4 (Web Text))

Max Activating Token Index: 468

Text #13

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.6140. Min Act: -0.0001

Data Index: 1176276 (C4 (Web Text))

Max Activating Token Index: 163

Text #14

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.6315. Min Act: -0.0001

Data Index: 443883 (C4 (Web Text))

Max Activating Token Index: 81

Text #15

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.6220. Min Act: -0.0001

Data Index: 436464 (C4 (Web Text))

Max Activating Token Index: 313

Text #16

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.6546. Min Act: -0.0001

Data Index: 1294216 (C4 (Web Text))

Max Activating Token Index: 839

Text #17

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.6015. Min Act: -0.0001

Data Index: 702286 (C4 (Web Text))

Max Activating Token Index: 80

Text #18

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.6469. Min Act: -0.0001

Data Index: 1118227 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.6973. Min Range: -0.6973

Max Act: 0.5853. Min Act: -0.0001

Data Index: 731089 (C4 (Web Text))

Max Activating Token Index: 309