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

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

Neuron 3029 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: 1.0031. Min Range: -1.0031

Max Act: 0.9446. Min Act: -0.0000

Data Index: 857760 (C4 (Web Text))

Max Activating Token Index: 162

Text #1

Max Range: 1.0031. Min Range: -1.0031

Max Act: 1.0031. Min Act: -0.0000

Data Index: 360684 (C4 (Web Text))

Max Activating Token Index: 542

Text #2

Max Range: 1.0031. Min Range: -1.0031

Max Act: 0.8613. Min Act: -0.0000

Data Index: 1148078 (C4 (Web Text))

Max Activating Token Index: 777

Text #3

Max Range: 1.0031. Min Range: -1.0031

Max Act: 0.8295. Min Act: -0.0000

Data Index: 914999 (C4 (Web Text))

Max Activating Token Index: 608

Text #4

Max Range: 1.0031. Min Range: -1.0031

Max Act: 0.7959. Min Act: -0.0000

Data Index: 439459 (C4 (Web Text))

Max Activating Token Index: 428

Text #5

Max Range: 1.0031. Min Range: -1.0031

Max Act: 0.7544. Min Act: -0.0000

Data Index: 134820 (C4 (Web Text))

Max Activating Token Index: 893

Text #6

Max Range: 1.0031. Min Range: -1.0031

Max Act: 0.7132. Min Act: -0.0001

Data Index: 892521 (C4 (Web Text))

Max Activating Token Index: 842

Text #7

Max Range: 1.0031. Min Range: -1.0031

Max Act: 0.7269. Min Act: -0.0000

Data Index: 219979 (C4 (Web Text))

Max Activating Token Index: 701

Text #8

Max Range: 1.0031. Min Range: -1.0031

Max Act: 0.7074. Min Act: -0.0000

Data Index: 205718 (C4 (Web Text))

Max Activating Token Index: 955

Text #9

Max Range: 1.0031. Min Range: -1.0031

Max Act: 0.7036. Min Act: -0.0000

Data Index: 702893 (C4 (Web Text))

Max Activating Token Index: 452

Text #10

Max Range: 1.0031. Min Range: -1.0031

Max Act: 0.7029. Min Act: -0.0000

Data Index: 151919 (C4 (Web Text))

Max Activating Token Index: 704

Text #11

Max Range: 1.0031. Min Range: -1.0031

Max Act: 0.7129. Min Act: -0.0000

Data Index: 548 (C4 (Web Text))

Max Activating Token Index: 907

Text #12

Max Range: 1.0031. Min Range: -1.0031

Max Act: 0.6910. Min Act: -0.0000

Data Index: 255639 (C4 (Web Text))

Max Activating Token Index: 557

Text #13

Max Range: 1.0031. Min Range: -1.0031

Max Act: 0.6841. Min Act: -0.0001

Data Index: 623132 (C4 (Web Text))

Max Activating Token Index: 259

Text #14

Max Range: 1.0031. Min Range: -1.0031

Max Act: 0.6517. Min Act: -0.0001

Data Index: 501023 (C4 (Web Text))

Max Activating Token Index: 771

Text #15

Max Range: 1.0031. Min Range: -1.0031

Max Act: 0.6647. Min Act: -0.0001

Data Index: 1044878 (C4 (Web Text))

Max Activating Token Index: 719

Text #16

Max Range: 1.0031. Min Range: -1.0031

Max Act: 0.6453. Min Act: -0.0001

Data Index: 1020435 (C4 (Web Text))

Max Activating Token Index: 187

Text #17

Max Range: 1.0031. Min Range: -1.0031

Max Act: 0.6657. Min Act: -0.0000

Data Index: 552374 (C4 (Web Text))

Max Activating Token Index: 915

Text #18

Max Range: 1.0031. Min Range: -1.0031

Max Act: 0.6637. Min Act: -0.0000

Data Index: 931941 (C4 (Web Text))

Max Activating Token Index: 437

Text #19

Max Range: 1.0031. Min Range: -1.0031

Max Act: 0.6583. Min Act: -0.0000

Data Index: 470356 (C4 (Web Text))

Max Activating Token Index: 695