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

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

Neuron 5205 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6090. Min Range: -0.6090

Max Act: 0.5833. Min Act: -0.0000

Data Index: 294541 (C4 (Web Text))

Max Activating Token Index: 151

Text #1

Max Range: 0.6090. Min Range: -0.6090

Max Act: 0.6090. Min Act: -0.0000

Data Index: 491397 (C4 (Web Text))

Max Activating Token Index: 559

Text #2

Max Range: 0.6090. Min Range: -0.6090

Max Act: 0.5821. Min Act: -0.0000

Data Index: 979207 (C4 (Web Text))

Max Activating Token Index: 837

Text #3

Max Range: 0.6090. Min Range: -0.6090

Max Act: 0.5845. Min Act: -0.0000

Data Index: 48674 (C4 (Web Text))

Max Activating Token Index: 740

Text #4

Max Range: 0.6090. Min Range: -0.6090

Max Act: 0.6018. Min Act: -0.0000

Data Index: 370593 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 0.6090. Min Range: -0.6090

Max Act: 0.5818. Min Act: -0.0000

Data Index: 875538 (C4 (Web Text))

Max Activating Token Index: 593

Text #6

Max Range: 0.6090. Min Range: -0.6090

Max Act: 0.5411. Min Act: -0.0000

Data Index: 1021633 (C4 (Web Text))

Max Activating Token Index: 99

Text #7

Max Range: 0.6090. Min Range: -0.6090

Max Act: 0.5683. Min Act: -0.0000

Data Index: 682313 (C4 (Web Text))

Max Activating Token Index: 590

Text #8

Max Range: 0.6090. Min Range: -0.6090

Max Act: 0.5710. Min Act: -0.0000

Data Index: 272507 (C4 (Web Text))

Max Activating Token Index: 227

Text #9

Max Range: 0.6090. Min Range: -0.6090

Max Act: 0.5363. Min Act: -0.0000

Data Index: 996354 (C4 (Web Text))

Max Activating Token Index: 110

Text #10

Max Range: 0.6090. Min Range: -0.6090

Max Act: 0.5525. Min Act: -0.0000

Data Index: 824213 (C4 (Web Text))

Max Activating Token Index: 708

Text #11

Max Range: 0.6090. Min Range: -0.6090

Max Act: 0.5349. Min Act: -0.0000

Data Index: 429173 (C4 (Web Text))

Max Activating Token Index: 86

Text #12

Max Range: 0.6090. Min Range: -0.6090

Max Act: 0.5179. Min Act: -0.0000

Data Index: 1235417 (C4 (Web Text))

Max Activating Token Index: 764

Text #13

Max Range: 0.6090. Min Range: -0.6090

Max Act: 0.5169. Min Act: -0.0000

Data Index: 58391 (C4 (Web Text))

Max Activating Token Index: 692

Text #14

Max Range: 0.6090. Min Range: -0.6090

Max Act: 0.5108. Min Act: -0.0000

Data Index: 367794 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 0.6090. Min Range: -0.6090

Max Act: 0.5158. Min Act: -0.0000

Data Index: 859589 (C4 (Web Text))

Max Activating Token Index: 26

Text #16

Max Range: 0.6090. Min Range: -0.6090

Max Act: 0.5030. Min Act: -0.0000

Data Index: 921938 (C4 (Web Text))

Max Activating Token Index: 729

Text #17

Max Range: 0.6090. Min Range: -0.6090

Max Act: 0.5122. Min Act: -0.0000

Data Index: 1235195 (C4 (Web Text))

Max Activating Token Index: 759

Text #18

Max Range: 0.6090. Min Range: -0.6090

Max Act: 0.4929. Min Act: -0.0000

Data Index: 900333 (C4 (Web Text))

Max Activating Token Index: 125

Text #19

Max Range: 0.6090. Min Range: -0.6090

Max Act: 0.5247. Min Act: -0.0000

Data Index: 496445 (C4 (Web Text))

Max Activating Token Index: 104