Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 785 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.6885. Min Act: -0.0000

Data Index: 949398 (C4 (Web Text))

Max Activating Token Index: 323

Text #1

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.6135. Min Act: -0.0000

Data Index: 252868 (C4 (Web Text))

Max Activating Token Index: 876

Text #2

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.6036. Min Act: -0.0000

Data Index: 388914 (C4 (Web Text))

Max Activating Token Index: 419

Text #3

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.6005. Min Act: -0.0000

Data Index: 767486 (C4 (Web Text))

Max Activating Token Index: 477

Text #4

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.5360. Min Act: -0.0000

Data Index: 955125 (C4 (Web Text))

Max Activating Token Index: 653

Text #5

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.4990. Min Act: -0.0000

Data Index: 1078727 (C4 (Web Text))

Max Activating Token Index: 599

Text #6

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.6441. Min Act: -0.0000

Data Index: 1394933 (Python Code)

Max Activating Token Index: 81

Text #7

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.5123. Min Act: -0.0000

Data Index: 1381377 (Python Code)

Max Activating Token Index: 571

Text #8

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.5671. Min Act: -0.0000

Data Index: 133461 (C4 (Web Text))

Max Activating Token Index: 875

Text #9

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.5519. Min Act: -0.0001

Data Index: 855423 (C4 (Web Text))

Max Activating Token Index: 923

Text #10

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.5502. Min Act: -0.0000

Data Index: 1083945 (C4 (Web Text))

Max Activating Token Index: 858

Text #11

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.5408. Min Act: -0.0000

Data Index: 353046 (C4 (Web Text))

Max Activating Token Index: 823

Text #12

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.5270. Min Act: -0.0001

Data Index: 1469115 (Python Code)

Max Activating Token Index: 444

Text #13

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.5693. Min Act: -0.0000

Data Index: 1613655 (Python Code)

Max Activating Token Index: 196

Text #14

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.5619. Min Act: -0.0001

Data Index: 415885 (C4 (Web Text))

Max Activating Token Index: 312

Text #15

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.5927. Min Act: -0.0000

Data Index: 807707 (C4 (Web Text))

Max Activating Token Index: 773

Text #16

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.5380. Min Act: -0.0000

Data Index: 57182 (C4 (Web Text))

Max Activating Token Index: 236

Text #17

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.4943. Min Act: -0.0001

Data Index: 1337296 (C4 (Web Text))

Max Activating Token Index: 114

Text #18

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.5058. Min Act: -0.0001

Data Index: 410811 (C4 (Web Text))

Max Activating Token Index: 218

Text #19

Max Range: 1.6885. Min Range: -1.6885

Max Act: 1.4873. Min Act: -0.0001

Data Index: 264025 (C4 (Web Text))

Max Activating Token Index: 849