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

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

Neuron 4086 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2902. Min Act: -0.0001

Data Index: 567604 (C4 (Web Text))

Max Activating Token Index: 678

Text #1

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2584. Min Act: -0.0001

Data Index: 143795 (C4 (Web Text))

Max Activating Token Index: 411

Text #2

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2728. Min Act: -0.0001

Data Index: 822668 (C4 (Web Text))

Max Activating Token Index: 503

Text #3

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2302. Min Act: -0.0000

Data Index: 1073329 (C4 (Web Text))

Max Activating Token Index: 598

Text #4

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2134. Min Act: -0.0000

Data Index: 441278 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1960. Min Act: -0.0001

Data Index: 136431 (C4 (Web Text))

Max Activating Token Index: 378

Text #6

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2156. Min Act: -0.0001

Data Index: 335902 (C4 (Web Text))

Max Activating Token Index: 415

Text #7

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1920. Min Act: -0.0000

Data Index: 1137997 (C4 (Web Text))

Max Activating Token Index: 834

Text #8

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1978. Min Act: -0.0000

Data Index: 988235 (C4 (Web Text))

Max Activating Token Index: 725

Text #9

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2076. Min Act: -0.0001

Data Index: 56191 (C4 (Web Text))

Max Activating Token Index: 487

Text #10

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1961. Min Act: -0.0000

Data Index: 1307882 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2045. Min Act: -0.0001

Data Index: 355799 (C4 (Web Text))

Max Activating Token Index: 762

Text #12

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1953. Min Act: -0.0001

Data Index: 483801 (C4 (Web Text))

Max Activating Token Index: 331

Text #13

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1850. Min Act: -0.0000

Data Index: 688311 (C4 (Web Text))

Max Activating Token Index: 1019

Text #14

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1722. Min Act: -0.0000

Data Index: 965755 (C4 (Web Text))

Max Activating Token Index: 385

Text #15

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1746. Min Act: -0.0001

Data Index: 1494024 (Python Code)

Max Activating Token Index: 226

Text #16

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1826. Min Act: -0.0000

Data Index: 1058807 (C4 (Web Text))

Max Activating Token Index: 756

Text #17

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1798. Min Act: -0.0001

Data Index: 270020 (C4 (Web Text))

Max Activating Token Index: 686

Text #18

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1897. Min Act: -0.0000

Data Index: 1223722 (C4 (Web Text))

Max Activating Token Index: 129

Text #19

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1982. Min Act: -0.0000

Data Index: 1152900 (C4 (Web Text))

Max Activating Token Index: 199