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

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

Neuron 4269 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4531. Min Range: -1.4531

Max Act: 1.4531. Min Act: -0.0000

Data Index: 315365 (C4 (Web Text))

Max Activating Token Index: 722

Text #1

Max Range: 1.4531. Min Range: -1.4531

Max Act: 1.3776. Min Act: -0.0000

Data Index: 431543 (C4 (Web Text))

Max Activating Token Index: 728

Text #2

Max Range: 1.4531. Min Range: -1.4531

Max Act: 1.2319. Min Act: -0.0000

Data Index: 99033 (C4 (Web Text))

Max Activating Token Index: 216

Text #3

Max Range: 1.4531. Min Range: -1.4531

Max Act: 1.1925. Min Act: -0.0000

Data Index: 904560 (C4 (Web Text))

Max Activating Token Index: 1009

Text #4

Max Range: 1.4531. Min Range: -1.4531

Max Act: 1.1671. Min Act: -0.0000

Data Index: 899345 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 1.4531. Min Range: -1.4531

Max Act: 1.0781. Min Act: -0.0000

Data Index: 998735 (C4 (Web Text))

Max Activating Token Index: 85

Text #6

Max Range: 1.4531. Min Range: -1.4531

Max Act: 0.9435. Min Act: -0.0000

Data Index: 510184 (C4 (Web Text))

Max Activating Token Index: 66

Text #7

Max Range: 1.4531. Min Range: -1.4531

Max Act: 0.9803. Min Act: -0.0000

Data Index: 648705 (C4 (Web Text))

Max Activating Token Index: 36

Text #8

Max Range: 1.4531. Min Range: -1.4531

Max Act: 0.8881. Min Act: -0.0000

Data Index: 936623 (C4 (Web Text))

Max Activating Token Index: 910

Text #9

Max Range: 1.4531. Min Range: -1.4531

Max Act: 0.8806. Min Act: -0.0000

Data Index: 843668 (C4 (Web Text))

Max Activating Token Index: 128

Text #10

Max Range: 1.4531. Min Range: -1.4531

Max Act: 0.8814. Min Act: -0.0000

Data Index: 714455 (C4 (Web Text))

Max Activating Token Index: 843

Text #11

Max Range: 1.4531. Min Range: -1.4531

Max Act: 0.8896. Min Act: -0.0000

Data Index: 1277099 (C4 (Web Text))

Max Activating Token Index: 406

Text #12

Max Range: 1.4531. Min Range: -1.4531

Max Act: 0.9050. Min Act: -0.0000

Data Index: 966459 (C4 (Web Text))

Max Activating Token Index: 948

Text #13

Max Range: 1.4531. Min Range: -1.4531

Max Act: 0.9012. Min Act: -0.0000

Data Index: 874535 (C4 (Web Text))

Max Activating Token Index: 64

Text #14

Max Range: 1.4531. Min Range: -1.4531

Max Act: 0.7838. Min Act: -0.0000

Data Index: 846798 (C4 (Web Text))

Max Activating Token Index: 748

Text #15

Max Range: 1.4531. Min Range: -1.4531

Max Act: 0.8426. Min Act: -0.0000

Data Index: 860662 (C4 (Web Text))

Max Activating Token Index: 58

Text #16

Max Range: 1.4531. Min Range: -1.4531

Max Act: 0.7717. Min Act: -0.0000

Data Index: 971280 (C4 (Web Text))

Max Activating Token Index: 511

Text #17

Max Range: 1.4531. Min Range: -1.4531

Max Act: 0.7763. Min Act: -0.0000

Data Index: 33742 (C4 (Web Text))

Max Activating Token Index: 492

Text #18

Max Range: 1.4531. Min Range: -1.4531

Max Act: 0.7448. Min Act: -0.0000

Data Index: 603721 (C4 (Web Text))

Max Activating Token Index: 186

Text #19

Max Range: 1.4531. Min Range: -1.4531

Max Act: 0.7694. Min Act: -0.0000

Data Index: 1135177 (C4 (Web Text))

Max Activating Token Index: 348