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

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

Neuron 3472 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.6395. Min Act: -0.0003

Data Index: 682063 (C4 (Web Text))

Max Activating Token Index: 282

Text #1

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.5582. Min Act: -0.0003

Data Index: 47829 (C4 (Web Text))

Max Activating Token Index: 727

Text #2

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.5509. Min Act: -0.0003

Data Index: 1056779 (C4 (Web Text))

Max Activating Token Index: 728

Text #3

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.6895. Min Act: -0.0003

Data Index: 477323 (C4 (Web Text))

Max Activating Token Index: 641

Text #4

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.6583. Min Act: -0.0003

Data Index: 601757 (C4 (Web Text))

Max Activating Token Index: 755

Text #5

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.5134. Min Act: -0.0003

Data Index: 570442 (C4 (Web Text))

Max Activating Token Index: 588

Text #6

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.6190. Min Act: -0.0003

Data Index: 150016 (C4 (Web Text))

Max Activating Token Index: 387

Text #7

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.4942. Min Act: -0.0003

Data Index: 166128 (C4 (Web Text))

Max Activating Token Index: 356

Text #8

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.6025. Min Act: -0.0003

Data Index: 135277 (C4 (Web Text))

Max Activating Token Index: 820

Text #9

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.5459. Min Act: -0.0003

Data Index: 898689 (C4 (Web Text))

Max Activating Token Index: 99

Text #10

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.5621. Min Act: -0.0003

Data Index: 1085432 (C4 (Web Text))

Max Activating Token Index: 542

Text #11

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.5919. Min Act: -0.0003

Data Index: 1133075 (C4 (Web Text))

Max Activating Token Index: 1020

Text #12

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.5535. Min Act: -0.0003

Data Index: 786000 (C4 (Web Text))

Max Activating Token Index: 111

Text #13

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.5512. Min Act: -0.0003

Data Index: 330102 (C4 (Web Text))

Max Activating Token Index: 859

Text #14

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.5446. Min Act: -0.0003

Data Index: 518382 (C4 (Web Text))

Max Activating Token Index: 571

Text #15

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.5082. Min Act: -0.0003

Data Index: 903461 (C4 (Web Text))

Max Activating Token Index: 433

Text #16

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.5247. Min Act: -0.0004

Data Index: 1300400 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.5056. Min Act: -0.0003

Data Index: 321548 (C4 (Web Text))

Max Activating Token Index: 95

Text #18

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.5762. Min Act: -0.0003

Data Index: 496075 (C4 (Web Text))

Max Activating Token Index: 794

Text #19

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.5228. Min Act: -0.0003

Data Index: 248520 (C4 (Web Text))

Max Activating Token Index: 877