Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3686 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4232. Min Range: -1.4232

Max Act: 1.3971. Min Act: -0.0001

Data Index: 543597 (C4 (Web Text))

Max Activating Token Index: 867

Text #1

Max Range: 1.4232. Min Range: -1.4232

Max Act: 1.3670. Min Act: -0.0001

Data Index: 158892 (C4 (Web Text))

Max Activating Token Index: 954

Text #2

Max Range: 1.4232. Min Range: -1.4232

Max Act: 1.4232. Min Act: -0.0001

Data Index: 485607 (C4 (Web Text))

Max Activating Token Index: 471

Text #3

Max Range: 1.4232. Min Range: -1.4232

Max Act: 1.3762. Min Act: -0.0001

Data Index: 174976 (C4 (Web Text))

Max Activating Token Index: 437

Text #4

Max Range: 1.4232. Min Range: -1.4232

Max Act: 1.3749. Min Act: -0.0001

Data Index: 329677 (C4 (Web Text))

Max Activating Token Index: 771

Text #5

Max Range: 1.4232. Min Range: -1.4232

Max Act: 1.3679. Min Act: -0.0001

Data Index: 1554286 (Python Code)

Max Activating Token Index: 348

Text #6

Max Range: 1.4232. Min Range: -1.4232

Max Act: 1.2741. Min Act: -0.0001

Data Index: 331037 (C4 (Web Text))

Max Activating Token Index: 545

Text #7

Max Range: 1.4232. Min Range: -1.4232

Max Act: 1.2961. Min Act: -0.0001

Data Index: 240307 (C4 (Web Text))

Max Activating Token Index: 1012

Text #8

Max Range: 1.4232. Min Range: -1.4232

Max Act: 1.2954. Min Act: -0.0001

Data Index: 153985 (C4 (Web Text))

Max Activating Token Index: 800

Text #9

Max Range: 1.4232. Min Range: -1.4232

Max Act: 1.2948. Min Act: -0.0001

Data Index: 1126004 (C4 (Web Text))

Max Activating Token Index: 647

Text #10

Max Range: 1.4232. Min Range: -1.4232

Max Act: 1.2676. Min Act: -0.0001

Data Index: 327349 (C4 (Web Text))

Max Activating Token Index: 887

Text #11

Max Range: 1.4232. Min Range: -1.4232

Max Act: 1.2448. Min Act: -0.0001

Data Index: 1561627 (Python Code)

Max Activating Token Index: 721

Text #12

Max Range: 1.4232. Min Range: -1.4232

Max Act: 1.2236. Min Act: -0.0001

Data Index: 1004028 (C4 (Web Text))

Max Activating Token Index: 824

Text #13

Max Range: 1.4232. Min Range: -1.4232

Max Act: 1.1744. Min Act: -0.0001

Data Index: 41048 (C4 (Web Text))

Max Activating Token Index: 822

Text #14

Max Range: 1.4232. Min Range: -1.4232

Max Act: 1.1427. Min Act: -0.0001

Data Index: 610828 (C4 (Web Text))

Max Activating Token Index: 551

Text #15

Max Range: 1.4232. Min Range: -1.4232

Max Act: 1.0133. Min Act: -0.0001

Data Index: 318306 (C4 (Web Text))

Max Activating Token Index: 420

Text #16

Max Range: 1.4232. Min Range: -1.4232

Max Act: 1.2180. Min Act: -0.0001

Data Index: 556669 (C4 (Web Text))

Max Activating Token Index: 58

Text #17

Max Range: 1.4232. Min Range: -1.4232

Max Act: 1.1746. Min Act: -0.0001

Data Index: 956564 (C4 (Web Text))

Max Activating Token Index: 769

Text #18

Max Range: 1.4232. Min Range: -1.4232

Max Act: 1.1002. Min Act: -0.0001

Data Index: 1198184 (C4 (Web Text))

Max Activating Token Index: 438

Text #19

Max Range: 1.4232. Min Range: -1.4232

Max Act: 1.1170. Min Act: -0.0001

Data Index: 22104 (C4 (Web Text))

Max Activating Token Index: 255