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

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

Neuron 3785 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9097. Min Range: -0.9097

Max Act: 0.9097. Min Act: -0.0000

Data Index: 1002660 (C4 (Web Text))

Max Activating Token Index: 969

Text #1

Max Range: 0.9097. Min Range: -0.9097

Max Act: 0.9096. Min Act: -0.0001

Data Index: 955197 (C4 (Web Text))

Max Activating Token Index: 553

Text #2

Max Range: 0.9097. Min Range: -0.9097

Max Act: 0.7138. Min Act: -0.0000

Data Index: 1168474 (C4 (Web Text))

Max Activating Token Index: 866

Text #3

Max Range: 0.9097. Min Range: -0.9097

Max Act: 0.6850. Min Act: -0.0001

Data Index: 858703 (C4 (Web Text))

Max Activating Token Index: 459

Text #4

Max Range: 0.9097. Min Range: -0.9097

Max Act: 0.6919. Min Act: -0.0000

Data Index: 840397 (C4 (Web Text))

Max Activating Token Index: 764

Text #5

Max Range: 0.9097. Min Range: -0.9097

Max Act: 0.6644. Min Act: -0.0000

Data Index: 1037600 (C4 (Web Text))

Max Activating Token Index: 316

Text #6

Max Range: 0.9097. Min Range: -0.9097

Max Act: 0.6016. Min Act: -0.0001

Data Index: 304713 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 0.9097. Min Range: -0.9097

Max Act: 0.5905. Min Act: -0.0000

Data Index: 1221150 (C4 (Web Text))

Max Activating Token Index: 708

Text #8

Max Range: 0.9097. Min Range: -0.9097

Max Act: 0.5388. Min Act: -0.0001

Data Index: 68634 (C4 (Web Text))

Max Activating Token Index: 268

Text #9

Max Range: 0.9097. Min Range: -0.9097

Max Act: 0.5534. Min Act: -0.0001

Data Index: 317711 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 0.9097. Min Range: -0.9097

Max Act: 0.5364. Min Act: -0.0001

Data Index: 24028 (C4 (Web Text))

Max Activating Token Index: 417

Text #11

Max Range: 0.9097. Min Range: -0.9097

Max Act: 0.5318. Min Act: -0.0001

Data Index: 842004 (C4 (Web Text))

Max Activating Token Index: 282

Text #12

Max Range: 0.9097. Min Range: -0.9097

Max Act: 0.4950. Min Act: -0.0000

Data Index: 1302653 (C4 (Web Text))

Max Activating Token Index: 447

Text #13

Max Range: 0.9097. Min Range: -0.9097

Max Act: 0.5186. Min Act: -0.0001

Data Index: 968678 (C4 (Web Text))

Max Activating Token Index: 117

Text #14

Max Range: 0.9097. Min Range: -0.9097

Max Act: 0.5064. Min Act: -0.0001

Data Index: 249258 (C4 (Web Text))

Max Activating Token Index: 920

Text #15

Max Range: 0.9097. Min Range: -0.9097

Max Act: 0.4428. Min Act: -0.0001

Data Index: 1205979 (C4 (Web Text))

Max Activating Token Index: 751

Text #16

Max Range: 0.9097. Min Range: -0.9097

Max Act: 0.4866. Min Act: -0.0000

Data Index: 767575 (C4 (Web Text))

Max Activating Token Index: 557

Text #17

Max Range: 0.9097. Min Range: -0.9097

Max Act: 0.4721. Min Act: -0.0001

Data Index: 453980 (C4 (Web Text))

Max Activating Token Index: 707

Text #18

Max Range: 0.9097. Min Range: -0.9097

Max Act: 0.5052. Min Act: -0.0000

Data Index: 687580 (C4 (Web Text))

Max Activating Token Index: 158

Text #19

Max Range: 0.9097. Min Range: -0.9097

Max Act: 0.5017. Min Act: -0.0000

Data Index: 813051 (C4 (Web Text))

Max Activating Token Index: 203