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

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

Neuron 1005 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: 1.6287. Min Range: -1.6287

Max Act: 1.6287. Min Act: -0.0000

Data Index: 359795 (C4 (Web Text))

Max Activating Token Index: 547

Text #1

Max Range: 1.6287. Min Range: -1.6287

Max Act: 1.2950. Min Act: -0.0000

Data Index: 730500 (C4 (Web Text))

Max Activating Token Index: 778

Text #2

Max Range: 1.6287. Min Range: -1.6287

Max Act: 1.2732. Min Act: -0.0000

Data Index: 1070752 (C4 (Web Text))

Max Activating Token Index: 135

Text #3

Max Range: 1.6287. Min Range: -1.6287

Max Act: 1.1677. Min Act: -0.0000

Data Index: 251107 (C4 (Web Text))

Max Activating Token Index: 240

Text #4

Max Range: 1.6287. Min Range: -1.6287

Max Act: 1.0133. Min Act: -0.0000

Data Index: 1046166 (C4 (Web Text))

Max Activating Token Index: 876

Text #5

Max Range: 1.6287. Min Range: -1.6287

Max Act: 1.0176. Min Act: -0.0000

Data Index: 110350 (C4 (Web Text))

Max Activating Token Index: 934

Text #6

Max Range: 1.6287. Min Range: -1.6287

Max Act: 0.8808. Min Act: -0.0000

Data Index: 1210389 (C4 (Web Text))

Max Activating Token Index: 209

Text #7

Max Range: 1.6287. Min Range: -1.6287

Max Act: 1.0607. Min Act: -0.0000

Data Index: 407940 (C4 (Web Text))

Max Activating Token Index: 507

Text #8

Max Range: 1.6287. Min Range: -1.6287

Max Act: 0.9578. Min Act: -0.0000

Data Index: 796849 (C4 (Web Text))

Max Activating Token Index: 363

Text #9

Max Range: 1.6287. Min Range: -1.6287

Max Act: 0.9342. Min Act: -0.0000

Data Index: 1077881 (C4 (Web Text))

Max Activating Token Index: 734

Text #10

Max Range: 1.6287. Min Range: -1.6287

Max Act: 0.9240. Min Act: -0.0000

Data Index: 444077 (C4 (Web Text))

Max Activating Token Index: 835

Text #11

Max Range: 1.6287. Min Range: -1.6287

Max Act: 0.9521. Min Act: -0.0000

Data Index: 562838 (C4 (Web Text))

Max Activating Token Index: 506

Text #12

Max Range: 1.6287. Min Range: -1.6287

Max Act: 0.8600. Min Act: -0.0000

Data Index: 218484 (C4 (Web Text))

Max Activating Token Index: 723

Text #13

Max Range: 1.6287. Min Range: -1.6287

Max Act: 0.8633. Min Act: -0.0000

Data Index: 1204889 (C4 (Web Text))

Max Activating Token Index: 568

Text #14

Max Range: 1.6287. Min Range: -1.6287

Max Act: 0.8565. Min Act: -0.0000

Data Index: 1353211 (C4 (Web Text))

Max Activating Token Index: 546

Text #15

Max Range: 1.6287. Min Range: -1.6287

Max Act: 0.9011. Min Act: -0.0000

Data Index: 782861 (C4 (Web Text))

Max Activating Token Index: 428

Text #16

Max Range: 1.6287. Min Range: -1.6287

Max Act: 0.9280. Min Act: -0.0000

Data Index: 1466693 (Python Code)

Max Activating Token Index: 236

Text #17

Max Range: 1.6287. Min Range: -1.6287

Max Act: 0.9139. Min Act: -0.0000

Data Index: 1208480 (C4 (Web Text))

Max Activating Token Index: 533

Text #18

Max Range: 1.6287. Min Range: -1.6287

Max Act: 0.8378. Min Act: -0.0000

Data Index: 772315 (C4 (Web Text))

Max Activating Token Index: 527

Text #19

Max Range: 1.6287. Min Range: -1.6287

Max Act: 0.8872. Min Act: -0.0000

Data Index: 94805 (C4 (Web Text))

Max Activating Token Index: 606