Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 5061 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 9.6221. Min Range: -9.6221

Max Act: 9.6221. Min Act: -0.0000

Data Index: 375210 (C4 (Web Text))

Max Activating Token Index: 884

Text #1

Max Range: 9.6221. Min Range: -9.6221

Max Act: 8.9438. Min Act: -0.0000

Data Index: 564581 (C4 (Web Text))

Max Activating Token Index: 730

Text #2

Max Range: 9.6221. Min Range: -9.6221

Max Act: 9.3949. Min Act: -0.0000

Data Index: 313225 (C4 (Web Text))

Max Activating Token Index: 1010

Text #3

Max Range: 9.6221. Min Range: -9.6221

Max Act: 9.1972. Min Act: -0.0000

Data Index: 982393 (C4 (Web Text))

Max Activating Token Index: 643

Text #4

Max Range: 9.6221. Min Range: -9.6221

Max Act: 8.9378. Min Act: -0.0000

Data Index: 265557 (C4 (Web Text))

Max Activating Token Index: 536

Text #5

Max Range: 9.6221. Min Range: -9.6221

Max Act: 8.7532. Min Act: -0.0000

Data Index: 135089 (C4 (Web Text))

Max Activating Token Index: 551

Text #6

Max Range: 9.6221. Min Range: -9.6221

Max Act: 8.1948. Min Act: -0.0000

Data Index: 887586 (C4 (Web Text))

Max Activating Token Index: 843

Text #7

Max Range: 9.6221. Min Range: -9.6221

Max Act: 8.3653. Min Act: -0.0000

Data Index: 846510 (C4 (Web Text))

Max Activating Token Index: 624

Text #8

Max Range: 9.6221. Min Range: -9.6221

Max Act: 8.6840. Min Act: -0.0000

Data Index: 88521 (C4 (Web Text))

Max Activating Token Index: 722

Text #9

Max Range: 9.6221. Min Range: -9.6221

Max Act: 8.6527. Min Act: -0.0000

Data Index: 494643 (C4 (Web Text))

Max Activating Token Index: 592

Text #10

Max Range: 9.6221. Min Range: -9.6221

Max Act: 7.9164. Min Act: -0.0000

Data Index: 1131249 (C4 (Web Text))

Max Activating Token Index: 409

Text #11

Max Range: 9.6221. Min Range: -9.6221

Max Act: 7.8802. Min Act: -0.0000

Data Index: 460379 (C4 (Web Text))

Max Activating Token Index: 742

Text #12

Max Range: 9.6221. Min Range: -9.6221

Max Act: 7.1108. Min Act: -0.0000

Data Index: 1262800 (C4 (Web Text))

Max Activating Token Index: 823

Text #13

Max Range: 9.6221. Min Range: -9.6221

Max Act: 7.8986. Min Act: -0.0000

Data Index: 855321 (C4 (Web Text))

Max Activating Token Index: 556

Text #14

Max Range: 9.6221. Min Range: -9.6221

Max Act: 7.8601. Min Act: -0.0000

Data Index: 417695 (C4 (Web Text))

Max Activating Token Index: 501

Text #15

Max Range: 9.6221. Min Range: -9.6221

Max Act: 7.3193. Min Act: -0.0000

Data Index: 980675 (C4 (Web Text))

Max Activating Token Index: 696

Text #16

Max Range: 9.6221. Min Range: -9.6221

Max Act: 8.0028. Min Act: -0.0000

Data Index: 999011 (C4 (Web Text))

Max Activating Token Index: 657

Text #17

Max Range: 9.6221. Min Range: -9.6221

Max Act: 7.7217. Min Act: -0.0000

Data Index: 600855 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 9.6221. Min Range: -9.6221

Max Act: 6.7693. Min Act: -0.0000

Data Index: 1507864 (Python Code)

Max Activating Token Index: 377

Text #19

Max Range: 9.6221. Min Range: -9.6221

Max Act: 6.4530. Min Act: -0.0001

Data Index: 1499688 (Python Code)

Max Activating Token Index: 314