Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1748 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.8927. Min Act: -0.0001

Data Index: 867109 (C4 (Web Text))

Max Activating Token Index: 482

Text #1

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.7896. Min Act: -0.0001

Data Index: 320101 (C4 (Web Text))

Max Activating Token Index: 78

Text #2

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.7670. Min Act: -0.0001

Data Index: 1181928 (C4 (Web Text))

Max Activating Token Index: 608

Text #3

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.7173. Min Act: -0.0001

Data Index: 834453 (C4 (Web Text))

Max Activating Token Index: 8

Text #4

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.7036. Min Act: -0.0001

Data Index: 369448 (C4 (Web Text))

Max Activating Token Index: 142

Text #5

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.7270. Min Act: -0.0001

Data Index: 325093 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.7201. Min Act: -0.0001

Data Index: 819428 (C4 (Web Text))

Max Activating Token Index: 291

Text #7

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.7350. Min Act: -0.0001

Data Index: 967545 (C4 (Web Text))

Max Activating Token Index: 702

Text #8

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.6803. Min Act: -0.0001

Data Index: 750133 (C4 (Web Text))

Max Activating Token Index: 408

Text #9

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.6817. Min Act: -0.0001

Data Index: 996514 (C4 (Web Text))

Max Activating Token Index: 906

Text #10

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.6510. Min Act: -0.0001

Data Index: 1330423 (C4 (Web Text))

Max Activating Token Index: 531

Text #11

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.6793. Min Act: -0.0001

Data Index: 709057 (C4 (Web Text))

Max Activating Token Index: 45

Text #12

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.6999. Min Act: -0.0001

Data Index: 187800 (C4 (Web Text))

Max Activating Token Index: 845

Text #13

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.6636. Min Act: -0.0001

Data Index: 1309000 (C4 (Web Text))

Max Activating Token Index: 976

Text #14

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.6887. Min Act: -0.0001

Data Index: 92535 (C4 (Web Text))

Max Activating Token Index: 368

Text #15

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.6762. Min Act: -0.0001

Data Index: 1141711 (C4 (Web Text))

Max Activating Token Index: 351

Text #16

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.6422. Min Act: -0.0001

Data Index: 840820 (C4 (Web Text))

Max Activating Token Index: 655

Text #17

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.6506. Min Act: -0.0001

Data Index: 505720 (C4 (Web Text))

Max Activating Token Index: 337

Text #18

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.6233. Min Act: -0.0001

Data Index: 1098054 (C4 (Web Text))

Max Activating Token Index: 339

Text #19

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.6454. Min Act: -0.0001

Data Index: 1071517 (C4 (Web Text))

Max Activating Token Index: 749