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

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

Neuron 3409 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: 2.3063. Min Range: -2.3063

Max Act: 2.3063. Min Act: -0.0000

Data Index: 930657 (C4 (Web Text))

Max Activating Token Index: 771

Text #1

Max Range: 2.3063. Min Range: -2.3063

Max Act: 1.6308. Min Act: -0.0000

Data Index: 223433 (C4 (Web Text))

Max Activating Token Index: 656

Text #2

Max Range: 2.3063. Min Range: -2.3063

Max Act: 1.5770. Min Act: -0.0000

Data Index: 1219108 (C4 (Web Text))

Max Activating Token Index: 401

Text #3

Max Range: 2.3063. Min Range: -2.3063

Max Act: 1.5133. Min Act: -0.0000

Data Index: 1106393 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 2.3063. Min Range: -2.3063

Max Act: 1.5560. Min Act: -0.0000

Data Index: 1073726 (C4 (Web Text))

Max Activating Token Index: 853

Text #5

Max Range: 2.3063. Min Range: -2.3063

Max Act: 1.4403. Min Act: -0.0000

Data Index: 94542 (C4 (Web Text))

Max Activating Token Index: 535

Text #6

Max Range: 2.3063. Min Range: -2.3063

Max Act: 1.3194. Min Act: -0.0000

Data Index: 455924 (C4 (Web Text))

Max Activating Token Index: 187

Text #7

Max Range: 2.3063. Min Range: -2.3063

Max Act: 1.3220. Min Act: -0.0000

Data Index: 1014937 (C4 (Web Text))

Max Activating Token Index: 620

Text #8

Max Range: 2.3063. Min Range: -2.3063

Max Act: 1.3984. Min Act: 0.0000

Data Index: 270024 (C4 (Web Text))

Max Activating Token Index: 155

Text #9

Max Range: 2.3063. Min Range: -2.3063

Max Act: 1.3858. Min Act: -0.0000

Data Index: 1247698 (C4 (Web Text))

Max Activating Token Index: 444

Text #10

Max Range: 2.3063. Min Range: -2.3063

Max Act: 1.3466. Min Act: -0.0000

Data Index: 322948 (C4 (Web Text))

Max Activating Token Index: 665

Text #11

Max Range: 2.3063. Min Range: -2.3063

Max Act: 1.3292. Min Act: -0.0000

Data Index: 681912 (C4 (Web Text))

Max Activating Token Index: 943

Text #12

Max Range: 2.3063. Min Range: -2.3063

Max Act: 1.3205. Min Act: -0.0000

Data Index: 309258 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 2.3063. Min Range: -2.3063

Max Act: 1.1800. Min Act: -0.0000

Data Index: 1198360 (C4 (Web Text))

Max Activating Token Index: 840

Text #14

Max Range: 2.3063. Min Range: -2.3063

Max Act: 1.3622. Min Act: -0.0000

Data Index: 452984 (C4 (Web Text))

Max Activating Token Index: 1016

Text #15

Max Range: 2.3063. Min Range: -2.3063

Max Act: 1.2540. Min Act: -0.0000

Data Index: 745015 (C4 (Web Text))

Max Activating Token Index: 762

Text #16

Max Range: 2.3063. Min Range: -2.3063

Max Act: 1.2538. Min Act: -0.0000

Data Index: 409844 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 2.3063. Min Range: -2.3063

Max Act: 1.2480. Min Act: -0.0000

Data Index: 575884 (C4 (Web Text))

Max Activating Token Index: 542

Text #18

Max Range: 2.3063. Min Range: -2.3063

Max Act: 1.2355. Min Act: -0.0000

Data Index: 827369 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 2.3063. Min Range: -2.3063

Max Act: 1.2093. Min Act: -0.0000

Data Index: 320359 (C4 (Web Text))

Max Activating Token Index: 230