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

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

Neuron 4630 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5750. Min Range: -1.5750

Max Act: 1.5750. Min Act: -0.0000

Data Index: 712675 (C4 (Web Text))

Max Activating Token Index: 553

Text #1

Max Range: 1.5750. Min Range: -1.5750

Max Act: 1.2909. Min Act: -0.0000

Data Index: 781179 (C4 (Web Text))

Max Activating Token Index: 140

Text #2

Max Range: 1.5750. Min Range: -1.5750

Max Act: 1.2278. Min Act: 0.0000

Data Index: 960192 (C4 (Web Text))

Max Activating Token Index: 250

Text #3

Max Range: 1.5750. Min Range: -1.5750

Max Act: 1.2305. Min Act: -0.0000

Data Index: 624559 (C4 (Web Text))

Max Activating Token Index: 273

Text #4

Max Range: 1.5750. Min Range: -1.5750

Max Act: 1.1993. Min Act: 0.0000

Data Index: 246406 (C4 (Web Text))

Max Activating Token Index: 222

Text #5

Max Range: 1.5750. Min Range: -1.5750

Max Act: 1.2477. Min Act: -0.0000

Data Index: 525643 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 1.5750. Min Range: -1.5750

Max Act: 1.1167. Min Act: -0.0000

Data Index: 928695 (C4 (Web Text))

Max Activating Token Index: 753

Text #7

Max Range: 1.5750. Min Range: -1.5750

Max Act: 1.2092. Min Act: -0.0000

Data Index: 957319 (C4 (Web Text))

Max Activating Token Index: 740

Text #8

Max Range: 1.5750. Min Range: -1.5750

Max Act: 1.0956. Min Act: -0.0000

Data Index: 42748 (C4 (Web Text))

Max Activating Token Index: 417

Text #9

Max Range: 1.5750. Min Range: -1.5750

Max Act: 1.0941. Min Act: -0.0000

Data Index: 455573 (C4 (Web Text))

Max Activating Token Index: 351

Text #10

Max Range: 1.5750. Min Range: -1.5750

Max Act: 1.1274. Min Act: -0.0000

Data Index: 527782 (C4 (Web Text))

Max Activating Token Index: 180

Text #11

Max Range: 1.5750. Min Range: -1.5750

Max Act: 1.0537. Min Act: -0.0000

Data Index: 1350724 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 1.5750. Min Range: -1.5750

Max Act: 1.0523. Min Act: -0.0000

Data Index: 63175 (C4 (Web Text))

Max Activating Token Index: 780

Text #13

Max Range: 1.5750. Min Range: -1.5750

Max Act: 1.0437. Min Act: 0.0001

Data Index: 155903 (C4 (Web Text))

Max Activating Token Index: 160

Text #14

Max Range: 1.5750. Min Range: -1.5750

Max Act: 1.1115. Min Act: -0.0000

Data Index: 445395 (C4 (Web Text))

Max Activating Token Index: 590

Text #15

Max Range: 1.5750. Min Range: -1.5750

Max Act: 0.9714. Min Act: -0.0000

Data Index: 450583 (C4 (Web Text))

Max Activating Token Index: 603

Text #16

Max Range: 1.5750. Min Range: -1.5750

Max Act: 1.0119. Min Act: 0.0000

Data Index: 425700 (C4 (Web Text))

Max Activating Token Index: 869

Text #17

Max Range: 1.5750. Min Range: -1.5750

Max Act: 1.0794. Min Act: -0.0000

Data Index: 783058 (C4 (Web Text))

Max Activating Token Index: 847

Text #18

Max Range: 1.5750. Min Range: -1.5750

Max Act: 1.0227. Min Act: -0.0000

Data Index: 80870 (C4 (Web Text))

Max Activating Token Index: 300

Text #19

Max Range: 1.5750. Min Range: -1.5750

Max Act: 1.0101. Min Act: -0.0000

Data Index: 756758 (C4 (Web Text))

Max Activating Token Index: 538