Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4503 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 6.4109. Min Range: -6.4109

Max Act: 6.3773. Min Act: -0.0000

Data Index: 1281837 (C4 (Web Text))

Max Activating Token Index: 106

Text #1

Max Range: 6.4109. Min Range: -6.4109

Max Act: 6.4109. Min Act: -0.0000

Data Index: 501088 (C4 (Web Text))

Max Activating Token Index: 741

Text #2

Max Range: 6.4109. Min Range: -6.4109

Max Act: 5.8685. Min Act: -0.0000

Data Index: 600669 (C4 (Web Text))

Max Activating Token Index: 411

Text #3

Max Range: 6.4109. Min Range: -6.4109

Max Act: 5.6535. Min Act: -0.0000

Data Index: 73453 (C4 (Web Text))

Max Activating Token Index: 990

Text #4

Max Range: 6.4109. Min Range: -6.4109

Max Act: 5.8343. Min Act: -0.0000

Data Index: 316267 (C4 (Web Text))

Max Activating Token Index: 55

Text #5

Max Range: 6.4109. Min Range: -6.4109

Max Act: 5.6347. Min Act: -0.0000

Data Index: 586730 (C4 (Web Text))

Max Activating Token Index: 1001

Text #6

Max Range: 6.4109. Min Range: -6.4109

Max Act: 5.5632. Min Act: -0.0000

Data Index: 1059602 (C4 (Web Text))

Max Activating Token Index: 452

Text #7

Max Range: 6.4109. Min Range: -6.4109

Max Act: 5.6851. Min Act: -0.0000

Data Index: 848411 (C4 (Web Text))

Max Activating Token Index: 427

Text #8

Max Range: 6.4109. Min Range: -6.4109

Max Act: 5.6750. Min Act: -0.0000

Data Index: 506289 (C4 (Web Text))

Max Activating Token Index: 611

Text #9

Max Range: 6.4109. Min Range: -6.4109

Max Act: 5.4175. Min Act: -0.0000

Data Index: 1261593 (C4 (Web Text))

Max Activating Token Index: 5

Text #10

Max Range: 6.4109. Min Range: -6.4109

Max Act: 5.7954. Min Act: -0.0000

Data Index: 337641 (C4 (Web Text))

Max Activating Token Index: 611

Text #11

Max Range: 6.4109. Min Range: -6.4109

Max Act: 5.6942. Min Act: -0.0000

Data Index: 7129 (C4 (Web Text))

Max Activating Token Index: 712

Text #12

Max Range: 6.4109. Min Range: -6.4109

Max Act: 5.5434. Min Act: -0.0000

Data Index: 818795 (C4 (Web Text))

Max Activating Token Index: 771

Text #13

Max Range: 6.4109. Min Range: -6.4109

Max Act: 5.3749. Min Act: -0.0000

Data Index: 1169024 (C4 (Web Text))

Max Activating Token Index: 10

Text #14

Max Range: 6.4109. Min Range: -6.4109

Max Act: 5.1373. Min Act: -0.0000

Data Index: 927293 (C4 (Web Text))

Max Activating Token Index: 588

Text #15

Max Range: 6.4109. Min Range: -6.4109

Max Act: 5.3415. Min Act: -0.0000

Data Index: 42279 (C4 (Web Text))

Max Activating Token Index: 557

Text #16

Max Range: 6.4109. Min Range: -6.4109

Max Act: 5.5467. Min Act: -0.0000

Data Index: 658436 (C4 (Web Text))

Max Activating Token Index: 809

Text #17

Max Range: 6.4109. Min Range: -6.4109

Max Act: 5.3106. Min Act: -0.0000

Data Index: 813065 (C4 (Web Text))

Max Activating Token Index: 589

Text #18

Max Range: 6.4109. Min Range: -6.4109

Max Act: 5.2510. Min Act: -0.0000

Data Index: 970120 (C4 (Web Text))

Max Activating Token Index: 954

Text #19

Max Range: 6.4109. Min Range: -6.4109

Max Act: 5.2314. Min Act: -0.0000

Data Index: 1105382 (C4 (Web Text))

Max Activating Token Index: 846