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

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

Neuron 1270 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: 1.5113. Min Range: -1.5113

Max Act: 1.4489. Min Act: -0.0000

Data Index: 983756 (C4 (Web Text))

Max Activating Token Index: 972

Text #1

Max Range: 1.5113. Min Range: -1.5113

Max Act: 1.4987. Min Act: -0.0000

Data Index: 383303 (C4 (Web Text))

Max Activating Token Index: 360

Text #2

Max Range: 1.5113. Min Range: -1.5113

Max Act: 1.5113. Min Act: -0.0000

Data Index: 272316 (C4 (Web Text))

Max Activating Token Index: 274

Text #3

Max Range: 1.5113. Min Range: -1.5113

Max Act: 1.2473. Min Act: -0.0000

Data Index: 516180 (C4 (Web Text))

Max Activating Token Index: 708

Text #4

Max Range: 1.5113. Min Range: -1.5113

Max Act: 1.2272. Min Act: -0.0000

Data Index: 1327514 (C4 (Web Text))

Max Activating Token Index: 276

Text #5

Max Range: 1.5113. Min Range: -1.5113

Max Act: 1.0895. Min Act: -0.0000

Data Index: 495262 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 1.5113. Min Range: -1.5113

Max Act: 1.0429. Min Act: -0.0000

Data Index: 682115 (C4 (Web Text))

Max Activating Token Index: 656

Text #7

Max Range: 1.5113. Min Range: -1.5113

Max Act: 0.9955. Min Act: -0.0000

Data Index: 844176 (C4 (Web Text))

Max Activating Token Index: 881

Text #8

Max Range: 1.5113. Min Range: -1.5113

Max Act: 0.9424. Min Act: -0.0000

Data Index: 436064 (C4 (Web Text))

Max Activating Token Index: 642

Text #9

Max Range: 1.5113. Min Range: -1.5113

Max Act: 1.0728. Min Act: -0.0000

Data Index: 1089462 (C4 (Web Text))

Max Activating Token Index: 417

Text #10

Max Range: 1.5113. Min Range: -1.5113

Max Act: 0.9695. Min Act: -0.0000

Data Index: 631965 (C4 (Web Text))

Max Activating Token Index: 697

Text #11

Max Range: 1.5113. Min Range: -1.5113

Max Act: 1.0498. Min Act: -0.0000

Data Index: 480286 (C4 (Web Text))

Max Activating Token Index: 734

Text #12

Max Range: 1.5113. Min Range: -1.5113

Max Act: 0.9709. Min Act: -0.0000

Data Index: 613970 (C4 (Web Text))

Max Activating Token Index: 685

Text #13

Max Range: 1.5113. Min Range: -1.5113

Max Act: 0.9634. Min Act: -0.0000

Data Index: 1241989 (C4 (Web Text))

Max Activating Token Index: 818

Text #14

Max Range: 1.5113. Min Range: -1.5113

Max Act: 0.9641. Min Act: -0.0000

Data Index: 21967 (C4 (Web Text))

Max Activating Token Index: 605

Text #15

Max Range: 1.5113. Min Range: -1.5113

Max Act: 0.7769. Min Act: -0.0000

Data Index: 631303 (C4 (Web Text))

Max Activating Token Index: 175

Text #16

Max Range: 1.5113. Min Range: -1.5113

Max Act: 0.8084. Min Act: -0.0000

Data Index: 548522 (C4 (Web Text))

Max Activating Token Index: 24

Text #17

Max Range: 1.5113. Min Range: -1.5113

Max Act: 0.7811. Min Act: -0.0000

Data Index: 527918 (C4 (Web Text))

Max Activating Token Index: 641

Text #18

Max Range: 1.5113. Min Range: -1.5113

Max Act: 0.8554. Min Act: -0.0000

Data Index: 528910 (C4 (Web Text))

Max Activating Token Index: 235

Text #19

Max Range: 1.5113. Min Range: -1.5113

Max Act: 0.7909. Min Act: -0.0000

Data Index: 150827 (C4 (Web Text))

Max Activating Token Index: 615