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

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

Neuron 5924 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4899. Min Range: -0.4899

Max Act: 0.4899. Min Act: -0.0000

Data Index: 804032 (C4 (Web Text))

Max Activating Token Index: 1000

Text #1

Max Range: 0.4899. Min Range: -0.4899

Max Act: 0.4727. Min Act: -0.0000

Data Index: 1340298 (C4 (Web Text))

Max Activating Token Index: 597

Text #2

Max Range: 0.4899. Min Range: -0.4899

Max Act: 0.4604. Min Act: -0.0000

Data Index: 555336 (C4 (Web Text))

Max Activating Token Index: 474

Text #3

Max Range: 0.4899. Min Range: -0.4899

Max Act: 0.4713. Min Act: -0.0000

Data Index: 230774 (C4 (Web Text))

Max Activating Token Index: 422

Text #4

Max Range: 0.4899. Min Range: -0.4899

Max Act: 0.4214. Min Act: -0.0000

Data Index: 610272 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 0.4899. Min Range: -0.4899

Max Act: 0.4420. Min Act: -0.0000

Data Index: 369362 (C4 (Web Text))

Max Activating Token Index: 506

Text #6

Max Range: 0.4899. Min Range: -0.4899

Max Act: 0.4172. Min Act: -0.0000

Data Index: 938127 (C4 (Web Text))

Max Activating Token Index: 756

Text #7

Max Range: 0.4899. Min Range: -0.4899

Max Act: 0.4130. Min Act: -0.0000

Data Index: 856146 (C4 (Web Text))

Max Activating Token Index: 950

Text #8

Max Range: 0.4899. Min Range: -0.4899

Max Act: 0.3940. Min Act: -0.0000

Data Index: 604209 (C4 (Web Text))

Max Activating Token Index: 317

Text #9

Max Range: 0.4899. Min Range: -0.4899

Max Act: 0.4048. Min Act: -0.0000

Data Index: 412316 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 0.4899. Min Range: -0.4899

Max Act: 0.3753. Min Act: -0.0000

Data Index: 759682 (C4 (Web Text))

Max Activating Token Index: 489

Text #11

Max Range: 0.4899. Min Range: -0.4899

Max Act: 0.3713. Min Act: 0.0000

Data Index: 600838 (C4 (Web Text))

Max Activating Token Index: 114

Text #12

Max Range: 0.4899. Min Range: -0.4899

Max Act: 0.3672. Min Act: -0.0000

Data Index: 351424 (C4 (Web Text))

Max Activating Token Index: 413

Text #13

Max Range: 0.4899. Min Range: -0.4899

Max Act: 0.3747. Min Act: -0.0000

Data Index: 1209520 (C4 (Web Text))

Max Activating Token Index: 430

Text #14

Max Range: 0.4899. Min Range: -0.4899

Max Act: 0.3520. Min Act: -0.0000

Data Index: 149796 (C4 (Web Text))

Max Activating Token Index: 687

Text #15

Max Range: 0.4899. Min Range: -0.4899

Max Act: 0.3587. Min Act: -0.0000

Data Index: 1014957 (C4 (Web Text))

Max Activating Token Index: 186

Text #16

Max Range: 0.4899. Min Range: -0.4899

Max Act: 0.3570. Min Act: -0.0000

Data Index: 1231807 (C4 (Web Text))

Max Activating Token Index: 883

Text #17

Max Range: 0.4899. Min Range: -0.4899

Max Act: 0.3508. Min Act: -0.0000

Data Index: 32344 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 0.4899. Min Range: -0.4899

Max Act: 0.3546. Min Act: -0.0000

Data Index: 1096110 (C4 (Web Text))

Max Activating Token Index: 651

Text #19

Max Range: 0.4899. Min Range: -0.4899

Max Act: 0.3428. Min Act: -0.0000

Data Index: 107309 (C4 (Web Text))

Max Activating Token Index: 450