Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1123 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8735. Min Range: -0.8735

Max Act: 0.8661. Min Act: -0.0000

Data Index: 1019198 (C4 (Web Text))

Max Activating Token Index: 719

Text #1

Max Range: 0.8735. Min Range: -0.8735

Max Act: 0.8735. Min Act: -0.0000

Data Index: 655291 (C4 (Web Text))

Max Activating Token Index: 294

Text #2

Max Range: 0.8735. Min Range: -0.8735

Max Act: 0.8099. Min Act: -0.0000

Data Index: 1309238 (C4 (Web Text))

Max Activating Token Index: 382

Text #3

Max Range: 0.8735. Min Range: -0.8735

Max Act: 0.7619. Min Act: -0.0000

Data Index: 475444 (C4 (Web Text))

Max Activating Token Index: 710

Text #4

Max Range: 0.8735. Min Range: -0.8735

Max Act: 0.7691. Min Act: -0.0000

Data Index: 265875 (C4 (Web Text))

Max Activating Token Index: 141

Text #5

Max Range: 0.8735. Min Range: -0.8735

Max Act: 0.6731. Min Act: -0.0000

Data Index: 182733 (C4 (Web Text))

Max Activating Token Index: 525

Text #6

Max Range: 0.8735. Min Range: -0.8735

Max Act: 0.6630. Min Act: 0.0001

Data Index: 1012268 (C4 (Web Text))

Max Activating Token Index: 157

Text #7

Max Range: 0.8735. Min Range: -0.8735

Max Act: 0.7538. Min Act: -0.0000

Data Index: 975025 (C4 (Web Text))

Max Activating Token Index: 538

Text #8

Max Range: 0.8735. Min Range: -0.8735

Max Act: 0.7495. Min Act: -0.0000

Data Index: 619891 (C4 (Web Text))

Max Activating Token Index: 124

Text #9

Max Range: 0.8735. Min Range: -0.8735

Max Act: 0.6641. Min Act: 0.0000

Data Index: 902238 (C4 (Web Text))

Max Activating Token Index: 1021

Text #10

Max Range: 0.8735. Min Range: -0.8735

Max Act: 0.6387. Min Act: -0.0000

Data Index: 776276 (C4 (Web Text))

Max Activating Token Index: 430

Text #11

Max Range: 0.8735. Min Range: -0.8735

Max Act: 0.6567. Min Act: -0.0000

Data Index: 408522 (C4 (Web Text))

Max Activating Token Index: 356

Text #12

Max Range: 0.8735. Min Range: -0.8735

Max Act: 0.6152. Min Act: -0.0000

Data Index: 231621 (C4 (Web Text))

Max Activating Token Index: 721

Text #13

Max Range: 0.8735. Min Range: -0.8735

Max Act: 0.6219. Min Act: -0.0000

Data Index: 601992 (C4 (Web Text))

Max Activating Token Index: 864

Text #14

Max Range: 0.8735. Min Range: -0.8735

Max Act: 0.6560. Min Act: 0.0000

Data Index: 343511 (C4 (Web Text))

Max Activating Token Index: 913

Text #15

Max Range: 0.8735. Min Range: -0.8735

Max Act: 0.5757. Min Act: -0.0000

Data Index: 648146 (C4 (Web Text))

Max Activating Token Index: 384

Text #16

Max Range: 0.8735. Min Range: -0.8735

Max Act: 0.5008. Min Act: -0.0000

Data Index: 1044281 (C4 (Web Text))

Max Activating Token Index: 180

Text #17

Max Range: 0.8735. Min Range: -0.8735

Max Act: 0.5948. Min Act: 0.0000

Data Index: 1275031 (C4 (Web Text))

Max Activating Token Index: 477

Text #18

Max Range: 0.8735. Min Range: -0.8735

Max Act: 0.6173. Min Act: -0.0000

Data Index: 656072 (C4 (Web Text))

Max Activating Token Index: 600

Text #19

Max Range: 0.8735. Min Range: -0.8735

Max Act: 0.6280. Min Act: -0.0000

Data Index: 441665 (C4 (Web Text))

Max Activating Token Index: 107