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

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

Neuron 1434 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.8870. Min Act: -0.0000

Data Index: 100107 (C4 (Web Text))

Max Activating Token Index: 1009

Text #1

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.9062. Min Act: -0.0000

Data Index: 172321 (C4 (Web Text))

Max Activating Token Index: 497

Text #2

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.8549. Min Act: -0.0000

Data Index: 833062 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.8499. Min Act: -0.0000

Data Index: 72799 (C4 (Web Text))

Max Activating Token Index: 995

Text #4

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.8296. Min Act: -0.0001

Data Index: 441075 (C4 (Web Text))

Max Activating Token Index: 381

Text #5

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.7854. Min Act: -0.0000

Data Index: 979395 (C4 (Web Text))

Max Activating Token Index: 31

Text #6

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.7617. Min Act: -0.0001

Data Index: 1113914 (C4 (Web Text))

Max Activating Token Index: 702

Text #7

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.7318. Min Act: -0.0001

Data Index: 988595 (C4 (Web Text))

Max Activating Token Index: 367

Text #8

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.7739. Min Act: -0.0000

Data Index: 167161 (C4 (Web Text))

Max Activating Token Index: 1022

Text #9

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.7435. Min Act: -0.0000

Data Index: 588135 (C4 (Web Text))

Max Activating Token Index: 524

Text #10

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.7174. Min Act: -0.0001

Data Index: 509713 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.7079. Min Act: -0.0000

Data Index: 178400 (C4 (Web Text))

Max Activating Token Index: 807

Text #12

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.7334. Min Act: -0.0000

Data Index: 767189 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.7013. Min Act: -0.0001

Data Index: 295724 (C4 (Web Text))

Max Activating Token Index: 392

Text #14

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.6960. Min Act: -0.0000

Data Index: 596739 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.6909. Min Act: -0.0000

Data Index: 286939 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.6897. Min Act: -0.0001

Data Index: 602845 (C4 (Web Text))

Max Activating Token Index: 884

Text #17

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.6852. Min Act: -0.0000

Data Index: 23118 (C4 (Web Text))

Max Activating Token Index: 735

Text #18

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.6750. Min Act: -0.0001

Data Index: 273159 (C4 (Web Text))

Max Activating Token Index: 503

Text #19

Max Range: 0.9062. Min Range: -0.9062

Max Act: 0.6408. Min Act: -0.0000

Data Index: 484116 (C4 (Web Text))

Max Activating Token Index: 623