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

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

Neuron 51 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: 0.9031. Min Range: -0.9031

Max Act: 0.9031. Min Act: -0.0000

Data Index: 677575 (C4 (Web Text))

Max Activating Token Index: 85

Text #1

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.7638. Min Act: -0.0000

Data Index: 857873 (C4 (Web Text))

Max Activating Token Index: 474

Text #2

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.7635. Min Act: -0.0000

Data Index: 337659 (C4 (Web Text))

Max Activating Token Index: 480

Text #3

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.7345. Min Act: -0.0000

Data Index: 1112890 (C4 (Web Text))

Max Activating Token Index: 572

Text #4

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.6937. Min Act: -0.0000

Data Index: 342490 (C4 (Web Text))

Max Activating Token Index: 734

Text #5

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.6329. Min Act: 0.0000

Data Index: 955350 (C4 (Web Text))

Max Activating Token Index: 611

Text #6

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.6324. Min Act: -0.0000

Data Index: 1159999 (C4 (Web Text))

Max Activating Token Index: 265

Text #7

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.5842. Min Act: -0.0000

Data Index: 649302 (C4 (Web Text))

Max Activating Token Index: 186

Text #8

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.6210. Min Act: -0.0000

Data Index: 533551 (C4 (Web Text))

Max Activating Token Index: 634

Text #9

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.6201. Min Act: -0.0000

Data Index: 163764 (C4 (Web Text))

Max Activating Token Index: 124

Text #10

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.6205. Min Act: -0.0000

Data Index: 887600 (C4 (Web Text))

Max Activating Token Index: 289

Text #11

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.6092. Min Act: -0.0000

Data Index: 727314 (C4 (Web Text))

Max Activating Token Index: 303

Text #12

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.5851. Min Act: -0.0000

Data Index: 1338809 (C4 (Web Text))

Max Activating Token Index: 143

Text #13

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.5797. Min Act: -0.0000

Data Index: 487696 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.5818. Min Act: -0.0000

Data Index: 90488 (C4 (Web Text))

Max Activating Token Index: 375

Text #15

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.5962. Min Act: -0.0001

Data Index: 1239392 (C4 (Web Text))

Max Activating Token Index: 115

Text #16

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.5879. Min Act: -0.0000

Data Index: 693381 (C4 (Web Text))

Max Activating Token Index: 383

Text #17

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.5905. Min Act: -0.0000

Data Index: 486336 (C4 (Web Text))

Max Activating Token Index: 308

Text #18

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.5485. Min Act: -0.0000

Data Index: 964866 (C4 (Web Text))

Max Activating Token Index: 653

Text #19

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.5430. Min Act: -0.0000

Data Index: 1101010 (C4 (Web Text))

Max Activating Token Index: 727