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

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

Neuron 1303 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.7018. Min Act: -0.0001

Data Index: 790957 (C4 (Web Text))

Max Activating Token Index: 973

Text #1

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.7129. Min Act: -0.0001

Data Index: 64214 (C4 (Web Text))

Max Activating Token Index: 288

Text #2

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.7103. Min Act: -0.0001

Data Index: 1377883 (Python Code)

Max Activating Token Index: 1013

Text #3

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.7198. Min Act: -0.0001

Data Index: 223652 (C4 (Web Text))

Max Activating Token Index: 1008

Text #4

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.6423. Min Act: -0.0001

Data Index: 1537180 (Python Code)

Max Activating Token Index: 568

Text #5

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.5405. Min Act: -0.0000

Data Index: 568708 (C4 (Web Text))

Max Activating Token Index: 226

Text #6

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.5952. Min Act: -0.0000

Data Index: 494176 (C4 (Web Text))

Max Activating Token Index: 494

Text #7

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.6597. Min Act: -0.0001

Data Index: 1057201 (C4 (Web Text))

Max Activating Token Index: 1021

Text #8

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.6774. Min Act: -0.0000

Data Index: 445511 (C4 (Web Text))

Max Activating Token Index: 790

Text #9

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.5738. Min Act: -0.0001

Data Index: 667228 (C4 (Web Text))

Max Activating Token Index: 755

Text #10

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.5779. Min Act: -0.0001

Data Index: 1558454 (Python Code)

Max Activating Token Index: 959

Text #11

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.5803. Min Act: -0.0000

Data Index: 516539 (C4 (Web Text))

Max Activating Token Index: 208

Text #12

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.5612. Min Act: -0.0001

Data Index: 434568 (C4 (Web Text))

Max Activating Token Index: 133

Text #13

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.5712. Min Act: -0.0000

Data Index: 212578 (C4 (Web Text))

Max Activating Token Index: 770

Text #14

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.5726. Min Act: -0.0000

Data Index: 678043 (C4 (Web Text))

Max Activating Token Index: 728

Text #15

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.5021. Min Act: -0.0001

Data Index: 1459304 (Python Code)

Max Activating Token Index: 766

Text #16

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.5129. Min Act: -0.0001

Data Index: 1489314 (Python Code)

Max Activating Token Index: 97

Text #17

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.5347. Min Act: -0.0001

Data Index: 2238 (C4 (Web Text))

Max Activating Token Index: 597

Text #18

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.5254. Min Act: -0.0001

Data Index: 1626775 (Python Code)

Max Activating Token Index: 911

Text #19

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.5414. Min Act: -0.0000

Data Index: 466518 (C4 (Web Text))

Max Activating Token Index: 397