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

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

Neuron 3590 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8720. Min Range: -3.8720

Max Act: 3.8720. Min Act: -0.0000

Data Index: 60328 (C4 (Web Text))

Max Activating Token Index: 385

Text #1

Max Range: 3.8720. Min Range: -3.8720

Max Act: 3.5896. Min Act: -0.0000

Data Index: 1012003 (C4 (Web Text))

Max Activating Token Index: 669

Text #2

Max Range: 3.8720. Min Range: -3.8720

Max Act: 3.3784. Min Act: -0.0000

Data Index: 1053386 (C4 (Web Text))

Max Activating Token Index: 1006

Text #3

Max Range: 3.8720. Min Range: -3.8720

Max Act: 3.2868. Min Act: -0.0000

Data Index: 366105 (C4 (Web Text))

Max Activating Token Index: 758

Text #4

Max Range: 3.8720. Min Range: -3.8720

Max Act: 3.1258. Min Act: -0.0000

Data Index: 768173 (C4 (Web Text))

Max Activating Token Index: 929

Text #5

Max Range: 3.8720. Min Range: -3.8720

Max Act: 2.9701. Min Act: -0.0000

Data Index: 292185 (C4 (Web Text))

Max Activating Token Index: 487

Text #6

Max Range: 3.8720. Min Range: -3.8720

Max Act: 3.1269. Min Act: -0.0000

Data Index: 1346277 (C4 (Web Text))

Max Activating Token Index: 803

Text #7

Max Range: 3.8720. Min Range: -3.8720

Max Act: 3.0847. Min Act: -0.0000

Data Index: 866622 (C4 (Web Text))

Max Activating Token Index: 154

Text #8

Max Range: 3.8720. Min Range: -3.8720

Max Act: 3.0466. Min Act: -0.0000

Data Index: 1148785 (C4 (Web Text))

Max Activating Token Index: 748

Text #9

Max Range: 3.8720. Min Range: -3.8720

Max Act: 3.0213. Min Act: -0.0000

Data Index: 1196692 (C4 (Web Text))

Max Activating Token Index: 597

Text #10

Max Range: 3.8720. Min Range: -3.8720

Max Act: 3.1502. Min Act: -0.0000

Data Index: 1352026 (C4 (Web Text))

Max Activating Token Index: 840

Text #11

Max Range: 3.8720. Min Range: -3.8720

Max Act: 2.9463. Min Act: -0.0000

Data Index: 711032 (C4 (Web Text))

Max Activating Token Index: 258

Text #12

Max Range: 3.8720. Min Range: -3.8720

Max Act: 2.7731. Min Act: -0.0000

Data Index: 237161 (C4 (Web Text))

Max Activating Token Index: 638

Text #13

Max Range: 3.8720. Min Range: -3.8720

Max Act: 2.6019. Min Act: -0.0000

Data Index: 1147984 (C4 (Web Text))

Max Activating Token Index: 736

Text #14

Max Range: 3.8720. Min Range: -3.8720

Max Act: 2.6846. Min Act: -0.0000

Data Index: 960025 (C4 (Web Text))

Max Activating Token Index: 869

Text #15

Max Range: 3.8720. Min Range: -3.8720

Max Act: 2.6854. Min Act: -0.0000

Data Index: 638969 (C4 (Web Text))

Max Activating Token Index: 891

Text #16

Max Range: 3.8720. Min Range: -3.8720

Max Act: 2.6743. Min Act: -0.0000

Data Index: 1247073 (C4 (Web Text))

Max Activating Token Index: 980

Text #17

Max Range: 3.8720. Min Range: -3.8720

Max Act: 2.6737. Min Act: -0.0000

Data Index: 830170 (C4 (Web Text))

Max Activating Token Index: 627

Text #18

Max Range: 3.8720. Min Range: -3.8720

Max Act: 2.5357. Min Act: -0.0000

Data Index: 666617 (C4 (Web Text))

Max Activating Token Index: 367

Text #19

Max Range: 3.8720. Min Range: -3.8720

Max Act: 2.6279. Min Act: -0.0000

Data Index: 42452 (C4 (Web Text))

Max Activating Token Index: 903