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

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

Neuron 2622 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.7509. Min Act: -0.0003

Data Index: 776804 (C4 (Web Text))

Max Activating Token Index: 374

Text #1

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.5738. Min Act: -0.0003

Data Index: 368088 (C4 (Web Text))

Max Activating Token Index: 1015

Text #2

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.5220. Min Act: -0.0003

Data Index: 1058222 (C4 (Web Text))

Max Activating Token Index: 194

Text #3

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.5227. Min Act: -0.0003

Data Index: 397622 (C4 (Web Text))

Max Activating Token Index: 270

Text #4

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.5397. Min Act: -0.0003

Data Index: 476188 (C4 (Web Text))

Max Activating Token Index: 397

Text #5

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.5166. Min Act: -0.0003

Data Index: 1313486 (C4 (Web Text))

Max Activating Token Index: 81

Text #6

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.5486. Min Act: -0.0003

Data Index: 1153159 (C4 (Web Text))

Max Activating Token Index: 711

Text #7

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.5316. Min Act: -0.0003

Data Index: 63911 (C4 (Web Text))

Max Activating Token Index: 525

Text #8

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.5126. Min Act: -0.0003

Data Index: 963986 (C4 (Web Text))

Max Activating Token Index: 87

Text #9

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.5247. Min Act: -0.0003

Data Index: 303877 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.4922. Min Act: -0.0003

Data Index: 500443 (C4 (Web Text))

Max Activating Token Index: 354

Text #11

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.4892. Min Act: -0.0003

Data Index: 1050802 (C4 (Web Text))

Max Activating Token Index: 208

Text #12

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.5127. Min Act: -0.0003

Data Index: 141032 (C4 (Web Text))

Max Activating Token Index: 1020

Text #13

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.5131. Min Act: -0.0003

Data Index: 496343 (C4 (Web Text))

Max Activating Token Index: 167

Text #14

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.4924. Min Act: -0.0003

Data Index: 204082 (C4 (Web Text))

Max Activating Token Index: 481

Text #15

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.4984. Min Act: -0.0003

Data Index: 1208249 (C4 (Web Text))

Max Activating Token Index: 56

Text #16

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.4683. Min Act: -0.0003

Data Index: 1062069 (C4 (Web Text))

Max Activating Token Index: 592

Text #17

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.5634. Min Act: -0.0003

Data Index: 1296928 (C4 (Web Text))

Max Activating Token Index: 806

Text #18

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.4659. Min Act: -0.0003

Data Index: 220798 (C4 (Web Text))

Max Activating Token Index: 767

Text #19

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.5088. Min Act: -0.0003

Data Index: 769538 (C4 (Web Text))

Max Activating Token Index: 28