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

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

Neuron 2824 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5348. Min Range: -0.5348

Max Act: 0.5348. Min Act: -0.0000

Data Index: 629771 (C4 (Web Text))

Max Activating Token Index: 425

Text #1

Max Range: 0.5348. Min Range: -0.5348

Max Act: 0.4710. Min Act: -0.0000

Data Index: 772924 (C4 (Web Text))

Max Activating Token Index: 1003

Text #2

Max Range: 0.5348. Min Range: -0.5348

Max Act: 0.4667. Min Act: -0.0000

Data Index: 494256 (C4 (Web Text))

Max Activating Token Index: 1012

Text #3

Max Range: 0.5348. Min Range: -0.5348

Max Act: 0.4326. Min Act: -0.0000

Data Index: 884469 (C4 (Web Text))

Max Activating Token Index: 596

Text #4

Max Range: 0.5348. Min Range: -0.5348

Max Act: 0.4583. Min Act: -0.0000

Data Index: 865916 (C4 (Web Text))

Max Activating Token Index: 766

Text #5

Max Range: 0.5348. Min Range: -0.5348

Max Act: 0.4739. Min Act: -0.0000

Data Index: 1026357 (C4 (Web Text))

Max Activating Token Index: 352

Text #6

Max Range: 0.5348. Min Range: -0.5348

Max Act: 0.4325. Min Act: -0.0000

Data Index: 869619 (C4 (Web Text))

Max Activating Token Index: 647

Text #7

Max Range: 0.5348. Min Range: -0.5348

Max Act: 0.4265. Min Act: -0.0000

Data Index: 174550 (C4 (Web Text))

Max Activating Token Index: 518

Text #8

Max Range: 0.5348. Min Range: -0.5348

Max Act: 0.4390. Min Act: -0.0000

Data Index: 429496 (C4 (Web Text))

Max Activating Token Index: 932

Text #9

Max Range: 0.5348. Min Range: -0.5348

Max Act: 0.4002. Min Act: -0.0000

Data Index: 506719 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 0.5348. Min Range: -0.5348

Max Act: 0.4014. Min Act: -0.0000

Data Index: 752469 (C4 (Web Text))

Max Activating Token Index: 319

Text #11

Max Range: 0.5348. Min Range: -0.5348

Max Act: 0.3904. Min Act: -0.0000

Data Index: 1282517 (C4 (Web Text))

Max Activating Token Index: 578

Text #12

Max Range: 0.5348. Min Range: -0.5348

Max Act: 0.3891. Min Act: -0.0000

Data Index: 214377 (C4 (Web Text))

Max Activating Token Index: 635

Text #13

Max Range: 0.5348. Min Range: -0.5348

Max Act: 0.3721. Min Act: -0.0000

Data Index: 571735 (C4 (Web Text))

Max Activating Token Index: 236

Text #14

Max Range: 0.5348. Min Range: -0.5348

Max Act: 0.3998. Min Act: -0.0000

Data Index: 378841 (C4 (Web Text))

Max Activating Token Index: 86

Text #15

Max Range: 0.5348. Min Range: -0.5348

Max Act: 0.3799. Min Act: -0.0000

Data Index: 589096 (C4 (Web Text))

Max Activating Token Index: 771

Text #16

Max Range: 0.5348. Min Range: -0.5348

Max Act: 0.3918. Min Act: -0.0000

Data Index: 1135829 (C4 (Web Text))

Max Activating Token Index: 101

Text #17

Max Range: 0.5348. Min Range: -0.5348

Max Act: 0.3650. Min Act: -0.0000

Data Index: 399824 (C4 (Web Text))

Max Activating Token Index: 898

Text #18

Max Range: 0.5348. Min Range: -0.5348

Max Act: 0.3715. Min Act: -0.0000

Data Index: 659932 (C4 (Web Text))

Max Activating Token Index: 1018

Text #19

Max Range: 0.5348. Min Range: -0.5348

Max Act: 0.3755. Min Act: -0.0000

Data Index: 141053 (C4 (Web Text))

Max Activating Token Index: 501