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

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

Neuron 4420 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: 1.5570. Min Range: -1.5570

Max Act: 1.5066. Min Act: -0.0000

Data Index: 197520 (C4 (Web Text))

Max Activating Token Index: 379

Text #1

Max Range: 1.5570. Min Range: -1.5570

Max Act: 1.5570. Min Act: -0.0000

Data Index: 329350 (C4 (Web Text))

Max Activating Token Index: 297

Text #2

Max Range: 1.5570. Min Range: -1.5570

Max Act: 1.4937. Min Act: -0.0000

Data Index: 950809 (C4 (Web Text))

Max Activating Token Index: 830

Text #3

Max Range: 1.5570. Min Range: -1.5570

Max Act: 1.2897. Min Act: -0.0000

Data Index: 1201758 (C4 (Web Text))

Max Activating Token Index: 519

Text #4

Max Range: 1.5570. Min Range: -1.5570

Max Act: 1.2775. Min Act: -0.0000

Data Index: 320871 (C4 (Web Text))

Max Activating Token Index: 243

Text #5

Max Range: 1.5570. Min Range: -1.5570

Max Act: 1.2969. Min Act: -0.0000

Data Index: 676586 (C4 (Web Text))

Max Activating Token Index: 789

Text #6

Max Range: 1.5570. Min Range: -1.5570

Max Act: 1.2850. Min Act: -0.0000

Data Index: 317600 (C4 (Web Text))

Max Activating Token Index: 90

Text #7

Max Range: 1.5570. Min Range: -1.5570

Max Act: 1.1359. Min Act: -0.0000

Data Index: 1313980 (C4 (Web Text))

Max Activating Token Index: 462

Text #8

Max Range: 1.5570. Min Range: -1.5570

Max Act: 1.1595. Min Act: -0.0000

Data Index: 1384159 (Python Code)

Max Activating Token Index: 117

Text #9

Max Range: 1.5570. Min Range: -1.5570

Max Act: 1.1996. Min Act: -0.0000

Data Index: 222629 (C4 (Web Text))

Max Activating Token Index: 859

Text #10

Max Range: 1.5570. Min Range: -1.5570

Max Act: 1.0538. Min Act: -0.0000

Data Index: 188231 (C4 (Web Text))

Max Activating Token Index: 908

Text #11

Max Range: 1.5570. Min Range: -1.5570

Max Act: 1.0505. Min Act: -0.0000

Data Index: 270984 (C4 (Web Text))

Max Activating Token Index: 148

Text #12

Max Range: 1.5570. Min Range: -1.5570

Max Act: 0.9125. Min Act: -0.0000

Data Index: 181354 (C4 (Web Text))

Max Activating Token Index: 801

Text #13

Max Range: 1.5570. Min Range: -1.5570

Max Act: 1.1264. Min Act: -0.0000

Data Index: 1066158 (C4 (Web Text))

Max Activating Token Index: 145

Text #14

Max Range: 1.5570. Min Range: -1.5570

Max Act: 1.0762. Min Act: -0.0000

Data Index: 1592296 (Python Code)

Max Activating Token Index: 131

Text #15

Max Range: 1.5570. Min Range: -1.5570

Max Act: 1.0693. Min Act: -0.0000

Data Index: 876355 (C4 (Web Text))

Max Activating Token Index: 148

Text #16

Max Range: 1.5570. Min Range: -1.5570

Max Act: 1.1729. Min Act: -0.0000

Data Index: 664896 (C4 (Web Text))

Max Activating Token Index: 56

Text #17

Max Range: 1.5570. Min Range: -1.5570

Max Act: 0.9182. Min Act: -0.0000

Data Index: 933661 (C4 (Web Text))

Max Activating Token Index: 891

Text #18

Max Range: 1.5570. Min Range: -1.5570

Max Act: 1.0070. Min Act: -0.0000

Data Index: 291717 (C4 (Web Text))

Max Activating Token Index: 1010

Text #19

Max Range: 1.5570. Min Range: -1.5570

Max Act: 0.9640. Min Act: -0.0000

Data Index: 47847 (C4 (Web Text))

Max Activating Token Index: 265