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

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

Neuron 363 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.4736. Min Act: -0.0001

Data Index: 695433 (C4 (Web Text))

Max Activating Token Index: 848

Text #1

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.4998. Min Act: -0.0001

Data Index: 190598 (C4 (Web Text))

Max Activating Token Index: 961

Text #2

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.4619. Min Act: -0.0000

Data Index: 311927 (C4 (Web Text))

Max Activating Token Index: 591

Text #3

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.4489. Min Act: -0.0000

Data Index: 1214495 (C4 (Web Text))

Max Activating Token Index: 885

Text #4

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.4320. Min Act: -0.0000

Data Index: 834380 (C4 (Web Text))

Max Activating Token Index: 660

Text #5

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.4313. Min Act: -0.0001

Data Index: 284748 (C4 (Web Text))

Max Activating Token Index: 449

Text #6

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.4355. Min Act: -0.0000

Data Index: 569150 (C4 (Web Text))

Max Activating Token Index: 190

Text #7

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.4342. Min Act: 0.0000

Data Index: 1172486 (C4 (Web Text))

Max Activating Token Index: 780

Text #8

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.4051. Min Act: -0.0000

Data Index: 343205 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.4144. Min Act: -0.0001

Data Index: 668212 (C4 (Web Text))

Max Activating Token Index: 1002

Text #10

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.4191. Min Act: -0.0000

Data Index: 1289105 (C4 (Web Text))

Max Activating Token Index: 741

Text #11

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.4005. Min Act: -0.0000

Data Index: 365255 (C4 (Web Text))

Max Activating Token Index: 89

Text #12

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.3974. Min Act: -0.0001

Data Index: 326387 (C4 (Web Text))

Max Activating Token Index: 386

Text #13

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.4050. Min Act: -0.0000

Data Index: 800408 (C4 (Web Text))

Max Activating Token Index: 77

Text #14

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.4011. Min Act: -0.0000

Data Index: 905709 (C4 (Web Text))

Max Activating Token Index: 353

Text #15

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.3769. Min Act: -0.0000

Data Index: 1037538 (C4 (Web Text))

Max Activating Token Index: 429

Text #16

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.3986. Min Act: -0.0000

Data Index: 1074097 (C4 (Web Text))

Max Activating Token Index: 543

Text #17

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.3840. Min Act: -0.0000

Data Index: 44690 (C4 (Web Text))

Max Activating Token Index: 873

Text #18

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.3848. Min Act: -0.0001

Data Index: 19344 (C4 (Web Text))

Max Activating Token Index: 302

Text #19

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.3852. Min Act: -0.0000

Data Index: 186307 (C4 (Web Text))

Max Activating Token Index: 936