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

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

Neuron 130 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0348. Min Range: -2.0348

Max Act: 2.0348. Min Act: -0.0000

Data Index: 789718 (C4 (Web Text))

Max Activating Token Index: 755

Text #1

Max Range: 2.0348. Min Range: -2.0348

Max Act: 1.8625. Min Act: -0.0000

Data Index: 642434 (C4 (Web Text))

Max Activating Token Index: 670

Text #2

Max Range: 2.0348. Min Range: -2.0348

Max Act: 1.6574. Min Act: -0.0000

Data Index: 185313 (C4 (Web Text))

Max Activating Token Index: 949

Text #3

Max Range: 2.0348. Min Range: -2.0348

Max Act: 1.6917. Min Act: -0.0000

Data Index: 542786 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 2.0348. Min Range: -2.0348

Max Act: 1.8087. Min Act: -0.0001

Data Index: 974339 (C4 (Web Text))

Max Activating Token Index: 860

Text #5

Max Range: 2.0348. Min Range: -2.0348

Max Act: 1.6678. Min Act: -0.0000

Data Index: 655547 (C4 (Web Text))

Max Activating Token Index: 365

Text #6

Max Range: 2.0348. Min Range: -2.0348

Max Act: 1.6935. Min Act: -0.0000

Data Index: 714692 (C4 (Web Text))

Max Activating Token Index: 929

Text #7

Max Range: 2.0348. Min Range: -2.0348

Max Act: 1.6878. Min Act: -0.0000

Data Index: 685803 (C4 (Web Text))

Max Activating Token Index: 461

Text #8

Max Range: 2.0348. Min Range: -2.0348

Max Act: 1.5760. Min Act: -0.0000

Data Index: 693099 (C4 (Web Text))

Max Activating Token Index: 138

Text #9

Max Range: 2.0348. Min Range: -2.0348

Max Act: 1.6769. Min Act: -0.0000

Data Index: 411944 (C4 (Web Text))

Max Activating Token Index: 291

Text #10

Max Range: 2.0348. Min Range: -2.0348

Max Act: 1.5750. Min Act: -0.0000

Data Index: 798114 (C4 (Web Text))

Max Activating Token Index: 364

Text #11

Max Range: 2.0348. Min Range: -2.0348

Max Act: 1.4668. Min Act: -0.0000

Data Index: 1063683 (C4 (Web Text))

Max Activating Token Index: 518

Text #12

Max Range: 2.0348. Min Range: -2.0348

Max Act: 1.5442. Min Act: -0.0000

Data Index: 1124714 (C4 (Web Text))

Max Activating Token Index: 268

Text #13

Max Range: 2.0348. Min Range: -2.0348

Max Act: 1.5407. Min Act: -0.0000

Data Index: 541613 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 2.0348. Min Range: -2.0348

Max Act: 1.4768. Min Act: -0.0000

Data Index: 935254 (C4 (Web Text))

Max Activating Token Index: 647

Text #15

Max Range: 2.0348. Min Range: -2.0348

Max Act: 1.4673. Min Act: -0.0000

Data Index: 809162 (C4 (Web Text))

Max Activating Token Index: 116

Text #16

Max Range: 2.0348. Min Range: -2.0348

Max Act: 1.4086. Min Act: -0.0000

Data Index: 389660 (C4 (Web Text))

Max Activating Token Index: 160

Text #17

Max Range: 2.0348. Min Range: -2.0348

Max Act: 1.4714. Min Act: -0.0000

Data Index: 488338 (C4 (Web Text))

Max Activating Token Index: 49

Text #18

Max Range: 2.0348. Min Range: -2.0348

Max Act: 1.5163. Min Act: -0.0000

Data Index: 505268 (C4 (Web Text))

Max Activating Token Index: 480

Text #19

Max Range: 2.0348. Min Range: -2.0348

Max Act: 1.3185. Min Act: -0.0000

Data Index: 793682 (C4 (Web Text))

Max Activating Token Index: 315