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

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

Neuron 307 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: 1.0435. Min Range: -1.0435

Max Act: 1.0435. Min Act: -0.0000

Data Index: 173931 (C4 (Web Text))

Max Activating Token Index: 668

Text #1

Max Range: 1.0435. Min Range: -1.0435

Max Act: 0.9076. Min Act: -0.0000

Data Index: 669751 (C4 (Web Text))

Max Activating Token Index: 670

Text #2

Max Range: 1.0435. Min Range: -1.0435

Max Act: 0.8724. Min Act: -0.0000

Data Index: 10261 (C4 (Web Text))

Max Activating Token Index: 908

Text #3

Max Range: 1.0435. Min Range: -1.0435

Max Act: 0.8562. Min Act: -0.0000

Data Index: 1101653 (C4 (Web Text))

Max Activating Token Index: 351

Text #4

Max Range: 1.0435. Min Range: -1.0435

Max Act: 0.8045. Min Act: -0.0000

Data Index: 596604 (C4 (Web Text))

Max Activating Token Index: 781

Text #5

Max Range: 1.0435. Min Range: -1.0435

Max Act: 0.8458. Min Act: -0.0000

Data Index: 1173806 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 1.0435. Min Range: -1.0435

Max Act: 0.8594. Min Act: -0.0001

Data Index: 1557599 (Python Code)

Max Activating Token Index: 207

Text #7

Max Range: 1.0435. Min Range: -1.0435

Max Act: 0.8288. Min Act: -0.0000

Data Index: 628251 (C4 (Web Text))

Max Activating Token Index: 368

Text #8

Max Range: 1.0435. Min Range: -1.0435

Max Act: 0.8148. Min Act: -0.0000

Data Index: 600543 (C4 (Web Text))

Max Activating Token Index: 375

Text #9

Max Range: 1.0435. Min Range: -1.0435

Max Act: 0.8065. Min Act: -0.0000

Data Index: 404776 (C4 (Web Text))

Max Activating Token Index: 811

Text #10

Max Range: 1.0435. Min Range: -1.0435

Max Act: 0.7787. Min Act: -0.0000

Data Index: 173890 (C4 (Web Text))

Max Activating Token Index: 922

Text #11

Max Range: 1.0435. Min Range: -1.0435

Max Act: 0.6983. Min Act: -0.0001

Data Index: 194166 (C4 (Web Text))

Max Activating Token Index: 1018

Text #12

Max Range: 1.0435. Min Range: -1.0435

Max Act: 0.7531. Min Act: -0.0001

Data Index: 740770 (C4 (Web Text))

Max Activating Token Index: 1001

Text #13

Max Range: 1.0435. Min Range: -1.0435

Max Act: 0.7773. Min Act: -0.0000

Data Index: 388405 (C4 (Web Text))

Max Activating Token Index: 626

Text #14

Max Range: 1.0435. Min Range: -1.0435

Max Act: 0.7129. Min Act: -0.0000

Data Index: 964961 (C4 (Web Text))

Max Activating Token Index: 725

Text #15

Max Range: 1.0435. Min Range: -1.0435

Max Act: 0.7359. Min Act: -0.0000

Data Index: 674684 (C4 (Web Text))

Max Activating Token Index: 461

Text #16

Max Range: 1.0435. Min Range: -1.0435

Max Act: 0.7140. Min Act: -0.0000

Data Index: 925041 (C4 (Web Text))

Max Activating Token Index: 912

Text #17

Max Range: 1.0435. Min Range: -1.0435

Max Act: 0.7567. Min Act: -0.0000

Data Index: 202562 (C4 (Web Text))

Max Activating Token Index: 809

Text #18

Max Range: 1.0435. Min Range: -1.0435

Max Act: 0.7258. Min Act: -0.0000

Data Index: 308105 (C4 (Web Text))

Max Activating Token Index: 936

Text #19

Max Range: 1.0435. Min Range: -1.0435

Max Act: 0.7051. Min Act: -0.0000

Data Index: 197045 (C4 (Web Text))

Max Activating Token Index: 275