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

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

Neuron 4374 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2198. Min Range: -2.2198

Max Act: 2.2198. Min Act: -0.0000

Data Index: 248237 (C4 (Web Text))

Max Activating Token Index: 258

Text #1

Max Range: 2.2198. Min Range: -2.2198

Max Act: 2.0391. Min Act: -0.0000

Data Index: 93616 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 2.2198. Min Range: -2.2198

Max Act: 2.1192. Min Act: -0.0000

Data Index: 681272 (C4 (Web Text))

Max Activating Token Index: 932

Text #3

Max Range: 2.2198. Min Range: -2.2198

Max Act: 1.9387. Min Act: -0.0000

Data Index: 776879 (C4 (Web Text))

Max Activating Token Index: 617

Text #4

Max Range: 2.2198. Min Range: -2.2198

Max Act: 1.9006. Min Act: -0.0000

Data Index: 488711 (C4 (Web Text))

Max Activating Token Index: 63

Text #5

Max Range: 2.2198. Min Range: -2.2198

Max Act: 1.8144. Min Act: -0.0000

Data Index: 212809 (C4 (Web Text))

Max Activating Token Index: 988

Text #6

Max Range: 2.2198. Min Range: -2.2198

Max Act: 1.8774. Min Act: -0.0000

Data Index: 509955 (C4 (Web Text))

Max Activating Token Index: 806

Text #7

Max Range: 2.2198. Min Range: -2.2198

Max Act: 1.8423. Min Act: -0.0000

Data Index: 19187 (C4 (Web Text))

Max Activating Token Index: 352

Text #8

Max Range: 2.2198. Min Range: -2.2198

Max Act: 1.8194. Min Act: -0.0000

Data Index: 442143 (C4 (Web Text))

Max Activating Token Index: 661

Text #9

Max Range: 2.2198. Min Range: -2.2198

Max Act: 1.7927. Min Act: -0.0000

Data Index: 812686 (C4 (Web Text))

Max Activating Token Index: 734

Text #10

Max Range: 2.2198. Min Range: -2.2198

Max Act: 1.7043. Min Act: -0.0000

Data Index: 395800 (C4 (Web Text))

Max Activating Token Index: 474

Text #11

Max Range: 2.2198. Min Range: -2.2198

Max Act: 1.6548. Min Act: -0.0000

Data Index: 265011 (C4 (Web Text))

Max Activating Token Index: 339

Text #12

Max Range: 2.2198. Min Range: -2.2198

Max Act: 1.6347. Min Act: -0.0000

Data Index: 1051767 (C4 (Web Text))

Max Activating Token Index: 674

Text #13

Max Range: 2.2198. Min Range: -2.2198

Max Act: 1.7347. Min Act: -0.0000

Data Index: 887040 (C4 (Web Text))

Max Activating Token Index: 147

Text #14

Max Range: 2.2198. Min Range: -2.2198

Max Act: 1.5480. Min Act: -0.0000

Data Index: 891320 (C4 (Web Text))

Max Activating Token Index: 810

Text #15

Max Range: 2.2198. Min Range: -2.2198

Max Act: 1.6245. Min Act: -0.0000

Data Index: 437702 (C4 (Web Text))

Max Activating Token Index: 801

Text #16

Max Range: 2.2198. Min Range: -2.2198

Max Act: 1.7101. Min Act: -0.0000

Data Index: 1192600 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 2.2198. Min Range: -2.2198

Max Act: 1.9068. Min Act: -0.0000

Data Index: 1274597 (C4 (Web Text))

Max Activating Token Index: 323

Text #18

Max Range: 2.2198. Min Range: -2.2198

Max Act: 1.5669. Min Act: -0.0000

Data Index: 1056987 (C4 (Web Text))

Max Activating Token Index: 543

Text #19

Max Range: 2.2198. Min Range: -2.2198

Max Act: 1.5476. Min Act: -0.0000

Data Index: 158892 (C4 (Web Text))

Max Activating Token Index: 755