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

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

Neuron 1908 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.7896. Min Act: -0.0000

Data Index: 682746 (C4 (Web Text))

Max Activating Token Index: 339

Text #1

Max Range: 1.0801. Min Range: -1.0801

Max Act: 1.0257. Min Act: -0.0000

Data Index: 704937 (C4 (Web Text))

Max Activating Token Index: 590

Text #2

Max Range: 1.0801. Min Range: -1.0801

Max Act: 1.0129. Min Act: -0.0000

Data Index: 1190989 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 1.0801. Min Range: -1.0801

Max Act: 1.0801. Min Act: -0.0000

Data Index: 705942 (C4 (Web Text))

Max Activating Token Index: 893

Text #4

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.9180. Min Act: -0.0000

Data Index: 436677 (C4 (Web Text))

Max Activating Token Index: 117

Text #5

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.9284. Min Act: -0.0000

Data Index: 1339441 (C4 (Web Text))

Max Activating Token Index: 534

Text #6

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.9177. Min Act: -0.0000

Data Index: 1291310 (C4 (Web Text))

Max Activating Token Index: 540

Text #7

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.8768. Min Act: -0.0000

Data Index: 439731 (C4 (Web Text))

Max Activating Token Index: 950

Text #8

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.8807. Min Act: -0.0000

Data Index: 102869 (C4 (Web Text))

Max Activating Token Index: 671

Text #9

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.8870. Min Act: -0.0000

Data Index: 932362 (C4 (Web Text))

Max Activating Token Index: 658

Text #10

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.8937. Min Act: -0.0000

Data Index: 51295 (C4 (Web Text))

Max Activating Token Index: 313

Text #11

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.8514. Min Act: -0.0000

Data Index: 147575 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.8663. Min Act: -0.0000

Data Index: 300861 (C4 (Web Text))

Max Activating Token Index: 920

Text #13

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.8064. Min Act: -0.0000

Data Index: 975747 (C4 (Web Text))

Max Activating Token Index: 886

Text #14

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.7768. Min Act: -0.0000

Data Index: 998674 (C4 (Web Text))

Max Activating Token Index: 147

Text #15

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.7735. Min Act: -0.0000

Data Index: 178120 (C4 (Web Text))

Max Activating Token Index: 403

Text #16

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.8364. Min Act: -0.0000

Data Index: 1185095 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.7846. Min Act: -0.0000

Data Index: 106276 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.8485. Min Act: -0.0000

Data Index: 482274 (C4 (Web Text))

Max Activating Token Index: 808

Text #19

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.8360. Min Act: -0.0000

Data Index: 653104 (C4 (Web Text))

Max Activating Token Index: 155