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

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

Neuron 924 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: 0.7507. Min Range: -0.7507

Max Act: 0.7320. Min Act: -0.0000

Data Index: 1038613 (C4 (Web Text))

Max Activating Token Index: 752

Text #1

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.7507. Min Act: -0.0001

Data Index: 594648 (C4 (Web Text))

Max Activating Token Index: 816

Text #2

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.7258. Min Act: -0.0000

Data Index: 849771 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.7071. Min Act: -0.0000

Data Index: 1335180 (C4 (Web Text))

Max Activating Token Index: 244

Text #4

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.6538. Min Act: -0.0000

Data Index: 579886 (C4 (Web Text))

Max Activating Token Index: 439

Text #5

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.7148. Min Act: -0.0000

Data Index: 1236544 (C4 (Web Text))

Max Activating Token Index: 234

Text #6

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.5977. Min Act: -0.0000

Data Index: 1251700 (C4 (Web Text))

Max Activating Token Index: 893

Text #7

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.5712. Min Act: -0.0000

Data Index: 62693 (C4 (Web Text))

Max Activating Token Index: 486

Text #8

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.5304. Min Act: -0.0000

Data Index: 314184 (C4 (Web Text))

Max Activating Token Index: 250

Text #9

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.5088. Min Act: -0.0000

Data Index: 1331626 (C4 (Web Text))

Max Activating Token Index: 388

Text #10

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.4745. Min Act: -0.0001

Data Index: 1163623 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.4642. Min Act: -0.0000

Data Index: 370681 (C4 (Web Text))

Max Activating Token Index: 636

Text #12

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.4879. Min Act: -0.0000

Data Index: 237968 (C4 (Web Text))

Max Activating Token Index: 226

Text #13

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.4765. Min Act: -0.0001

Data Index: 586914 (C4 (Web Text))

Max Activating Token Index: 852

Text #14

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.4541. Min Act: -0.0001

Data Index: 635340 (C4 (Web Text))

Max Activating Token Index: 727

Text #15

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.4087. Min Act: -0.0001

Data Index: 287454 (C4 (Web Text))

Max Activating Token Index: 646

Text #16

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.3058. Min Act: -0.0001

Data Index: 622894 (C4 (Web Text))

Max Activating Token Index: 737

Text #17

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.4315. Min Act: -0.0000

Data Index: 767166 (C4 (Web Text))

Max Activating Token Index: 586

Text #18

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.3626. Min Act: -0.0000

Data Index: 837954 (C4 (Web Text))

Max Activating Token Index: 944

Text #19

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.3483. Min Act: -0.0000

Data Index: 1018147 (C4 (Web Text))

Max Activating Token Index: 734