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

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

Neuron 279 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8226. Min Range: -0.8226

Max Act: 0.8226. Min Act: -0.0001

Data Index: 994129 (C4 (Web Text))

Max Activating Token Index: 168

Text #1

Max Range: 0.8226. Min Range: -0.8226

Max Act: 0.7414. Min Act: -0.0001

Data Index: 165704 (C4 (Web Text))

Max Activating Token Index: 76

Text #2

Max Range: 0.8226. Min Range: -0.8226

Max Act: 0.6596. Min Act: -0.0002

Data Index: 610812 (C4 (Web Text))

Max Activating Token Index: 834

Text #3

Max Range: 0.8226. Min Range: -0.8226

Max Act: 0.6481. Min Act: -0.0002

Data Index: 304813 (C4 (Web Text))

Max Activating Token Index: 414

Text #4

Max Range: 0.8226. Min Range: -0.8226

Max Act: 0.6082. Min Act: -0.0001

Data Index: 1012847 (C4 (Web Text))

Max Activating Token Index: 575

Text #5

Max Range: 0.8226. Min Range: -0.8226

Max Act: 0.6058. Min Act: -0.0001

Data Index: 305569 (C4 (Web Text))

Max Activating Token Index: 20

Text #6

Max Range: 0.8226. Min Range: -0.8226

Max Act: 0.6110. Min Act: -0.0001

Data Index: 1204590 (C4 (Web Text))

Max Activating Token Index: 991

Text #7

Max Range: 0.8226. Min Range: -0.8226

Max Act: 0.5151. Min Act: -0.0002

Data Index: 693449 (C4 (Web Text))

Max Activating Token Index: 746

Text #8

Max Range: 0.8226. Min Range: -0.8226

Max Act: 0.5697. Min Act: -0.0001

Data Index: 640853 (C4 (Web Text))

Max Activating Token Index: 606

Text #9

Max Range: 0.8226. Min Range: -0.8226

Max Act: 0.5982. Min Act: -0.0001

Data Index: 744817 (C4 (Web Text))

Max Activating Token Index: 517

Text #10

Max Range: 0.8226. Min Range: -0.8226

Max Act: 0.5560. Min Act: -0.0001

Data Index: 536873 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 0.8226. Min Range: -0.8226

Max Act: 0.5716. Min Act: -0.0001

Data Index: 539373 (C4 (Web Text))

Max Activating Token Index: 118

Text #12

Max Range: 0.8226. Min Range: -0.8226

Max Act: 0.5497. Min Act: -0.0001

Data Index: 322076 (C4 (Web Text))

Max Activating Token Index: 19

Text #13

Max Range: 0.8226. Min Range: -0.8226

Max Act: 0.5446. Min Act: -0.0001

Data Index: 299805 (C4 (Web Text))

Max Activating Token Index: 4

Text #14

Max Range: 0.8226. Min Range: -0.8226

Max Act: 0.5644. Min Act: -0.0001

Data Index: 866259 (C4 (Web Text))

Max Activating Token Index: 222

Text #15

Max Range: 0.8226. Min Range: -0.8226

Max Act: 0.5424. Min Act: -0.0001

Data Index: 978677 (C4 (Web Text))

Max Activating Token Index: 675

Text #16

Max Range: 0.8226. Min Range: -0.8226

Max Act: 0.5247. Min Act: -0.0001

Data Index: 587914 (C4 (Web Text))

Max Activating Token Index: 816

Text #17

Max Range: 0.8226. Min Range: -0.8226

Max Act: 0.5066. Min Act: -0.0001

Data Index: 1146540 (C4 (Web Text))

Max Activating Token Index: 729

Text #18

Max Range: 0.8226. Min Range: -0.8226

Max Act: 0.4851. Min Act: -0.0001

Data Index: 34822 (C4 (Web Text))

Max Activating Token Index: 853

Text #19

Max Range: 0.8226. Min Range: -0.8226

Max Act: 0.5012. Min Act: -0.0001

Data Index: 375695 (C4 (Web Text))

Max Activating Token Index: 131