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

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

Neuron 3213 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: 0.6681. Min Range: -0.6681

Max Act: 0.6681. Min Act: -0.0002

Data Index: 1045335 (C4 (Web Text))

Max Activating Token Index: 963

Text #1

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.6029. Min Act: -0.0001

Data Index: 987525 (C4 (Web Text))

Max Activating Token Index: 147

Text #2

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.5637. Min Act: -0.0001

Data Index: 1176559 (C4 (Web Text))

Max Activating Token Index: 705

Text #3

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.6324. Min Act: -0.0001

Data Index: 1314739 (C4 (Web Text))

Max Activating Token Index: 342

Text #4

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.5913. Min Act: -0.0001

Data Index: 899108 (C4 (Web Text))

Max Activating Token Index: 736

Text #5

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.5858. Min Act: -0.0002

Data Index: 435175 (C4 (Web Text))

Max Activating Token Index: 200

Text #6

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.6051. Min Act: -0.0001

Data Index: 1004549 (C4 (Web Text))

Max Activating Token Index: 197

Text #7

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.5415. Min Act: -0.0002

Data Index: 1155496 (C4 (Web Text))

Max Activating Token Index: 554

Text #8

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.6036. Min Act: -0.0002

Data Index: 913214 (C4 (Web Text))

Max Activating Token Index: 253

Text #9

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.5658. Min Act: -0.0002

Data Index: 134298 (C4 (Web Text))

Max Activating Token Index: 538

Text #10

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.5307. Min Act: -0.0001

Data Index: 904713 (C4 (Web Text))

Max Activating Token Index: 786

Text #11

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.5519. Min Act: -0.0001

Data Index: 212925 (C4 (Web Text))

Max Activating Token Index: 387

Text #12

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.5094. Min Act: -0.0001

Data Index: 1315303 (C4 (Web Text))

Max Activating Token Index: 970

Text #13

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.5523. Min Act: -0.0002

Data Index: 1163531 (C4 (Web Text))

Max Activating Token Index: 794

Text #14

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.5063. Min Act: -0.0001

Data Index: 210044 (C4 (Web Text))

Max Activating Token Index: 969

Text #15

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.5365. Min Act: -0.0001

Data Index: 32340 (C4 (Web Text))

Max Activating Token Index: 785

Text #16

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.4995. Min Act: -0.0001

Data Index: 1322669 (C4 (Web Text))

Max Activating Token Index: 605

Text #17

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.5718. Min Act: -0.0002

Data Index: 130238 (C4 (Web Text))

Max Activating Token Index: 89

Text #18

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.5170. Min Act: -0.0001

Data Index: 774683 (C4 (Web Text))

Max Activating Token Index: 496

Text #19

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.5000. Min Act: -0.0002

Data Index: 60921 (C4 (Web Text))

Max Activating Token Index: 302