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

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

Neuron 2471 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: 0.5383. Min Range: -0.5383

Max Act: 0.5126. Min Act: -0.0002

Data Index: 1270553 (C4 (Web Text))

Max Activating Token Index: 184

Text #1

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.5233. Min Act: -0.0002

Data Index: 364310 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.5116. Min Act: -0.0001

Data Index: 1117583 (C4 (Web Text))

Max Activating Token Index: 174

Text #3

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.4911. Min Act: -0.0002

Data Index: 978835 (C4 (Web Text))

Max Activating Token Index: 670

Text #4

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.4990. Min Act: -0.0002

Data Index: 248661 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.4778. Min Act: -0.0001

Data Index: 326652 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.4996. Min Act: -0.0001

Data Index: 350372 (C4 (Web Text))

Max Activating Token Index: 279

Text #7

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.4471. Min Act: -0.0001

Data Index: 225774 (C4 (Web Text))

Max Activating Token Index: 852

Text #8

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.4628. Min Act: -0.0002

Data Index: 377767 (C4 (Web Text))

Max Activating Token Index: 740

Text #9

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.5383. Min Act: -0.0001

Data Index: 777512 (C4 (Web Text))

Max Activating Token Index: 152

Text #10

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.4735. Min Act: -0.0002

Data Index: 345396 (C4 (Web Text))

Max Activating Token Index: 106

Text #11

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.4155. Min Act: -0.0002

Data Index: 371243 (C4 (Web Text))

Max Activating Token Index: 91

Text #12

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.4650. Min Act: -0.0002

Data Index: 766585 (C4 (Web Text))

Max Activating Token Index: 586

Text #13

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.4638. Min Act: -0.0001

Data Index: 288481 (C4 (Web Text))

Max Activating Token Index: 862

Text #14

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.4352. Min Act: -0.0001

Data Index: 781147 (C4 (Web Text))

Max Activating Token Index: 173

Text #15

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.4795. Min Act: -0.0002

Data Index: 414918 (C4 (Web Text))

Max Activating Token Index: 107

Text #16

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.4584. Min Act: -0.0002

Data Index: 1344882 (C4 (Web Text))

Max Activating Token Index: 894

Text #17

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.4580. Min Act: -0.0002

Data Index: 1048038 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.5191. Min Act: -0.0001

Data Index: 193285 (C4 (Web Text))

Max Activating Token Index: 140

Text #19

Max Range: 0.5383. Min Range: -0.5383

Max Act: 0.4703. Min Act: -0.0002

Data Index: 1314047 (C4 (Web Text))

Max Activating Token Index: 109