Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3393 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0018. Min Range: -1.0018

Max Act: 1.0018. Min Act: -0.0000

Data Index: 1282343 (C4 (Web Text))

Max Activating Token Index: 853

Text #1

Max Range: 1.0018. Min Range: -1.0018

Max Act: 0.9955. Min Act: -0.0001

Data Index: 780853 (C4 (Web Text))

Max Activating Token Index: 464

Text #2

Max Range: 1.0018. Min Range: -1.0018

Max Act: 0.9287. Min Act: -0.0001

Data Index: 14408 (C4 (Web Text))

Max Activating Token Index: 474

Text #3

Max Range: 1.0018. Min Range: -1.0018

Max Act: 0.8487. Min Act: -0.0001

Data Index: 1136257 (C4 (Web Text))

Max Activating Token Index: 830

Text #4

Max Range: 1.0018. Min Range: -1.0018

Max Act: 0.7870. Min Act: -0.0001

Data Index: 549043 (C4 (Web Text))

Max Activating Token Index: 109

Text #5

Max Range: 1.0018. Min Range: -1.0018

Max Act: 0.7502. Min Act: -0.0001

Data Index: 445934 (C4 (Web Text))

Max Activating Token Index: 523

Text #6

Max Range: 1.0018. Min Range: -1.0018

Max Act: 0.7218. Min Act: -0.0001

Data Index: 1340045 (C4 (Web Text))

Max Activating Token Index: 988

Text #7

Max Range: 1.0018. Min Range: -1.0018

Max Act: 0.7219. Min Act: -0.0001

Data Index: 832868 (C4 (Web Text))

Max Activating Token Index: 201

Text #8

Max Range: 1.0018. Min Range: -1.0018

Max Act: 0.7425. Min Act: -0.0001

Data Index: 479620 (C4 (Web Text))

Max Activating Token Index: 142

Text #9

Max Range: 1.0018. Min Range: -1.0018

Max Act: 0.7312. Min Act: -0.0001

Data Index: 215660 (C4 (Web Text))

Max Activating Token Index: 356

Text #10

Max Range: 1.0018. Min Range: -1.0018

Max Act: 0.6678. Min Act: -0.0001

Data Index: 1117020 (C4 (Web Text))

Max Activating Token Index: 456

Text #11

Max Range: 1.0018. Min Range: -1.0018

Max Act: 0.6774. Min Act: -0.0001

Data Index: 735399 (C4 (Web Text))

Max Activating Token Index: 872

Text #12

Max Range: 1.0018. Min Range: -1.0018

Max Act: 0.6069. Min Act: -0.0001

Data Index: 815533 (C4 (Web Text))

Max Activating Token Index: 585

Text #13

Max Range: 1.0018. Min Range: -1.0018

Max Act: 0.6879. Min Act: -0.0001

Data Index: 137581 (C4 (Web Text))

Max Activating Token Index: 150

Text #14

Max Range: 1.0018. Min Range: -1.0018

Max Act: 0.6645. Min Act: -0.0001

Data Index: 1267348 (C4 (Web Text))

Max Activating Token Index: 762

Text #15

Max Range: 1.0018. Min Range: -1.0018

Max Act: 0.6772. Min Act: -0.0001

Data Index: 497472 (C4 (Web Text))

Max Activating Token Index: 270

Text #16

Max Range: 1.0018. Min Range: -1.0018

Max Act: 0.6650. Min Act: -0.0000

Data Index: 85025 (C4 (Web Text))

Max Activating Token Index: 477

Text #17

Max Range: 1.0018. Min Range: -1.0018

Max Act: 0.6283. Min Act: -0.0001

Data Index: 424352 (C4 (Web Text))

Max Activating Token Index: 461

Text #18

Max Range: 1.0018. Min Range: -1.0018

Max Act: 0.6327. Min Act: -0.0000

Data Index: 571128 (C4 (Web Text))

Max Activating Token Index: 429

Text #19

Max Range: 1.0018. Min Range: -1.0018

Max Act: 0.6390. Min Act: -0.0001

Data Index: 63659 (C4 (Web Text))

Max Activating Token Index: 640