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

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

Neuron 1791 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.8404. Min Act: -0.0002

Data Index: 428821 (C4 (Web Text))

Max Activating Token Index: 69

Text #1

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.7930. Min Act: -0.0002

Data Index: 1215424 (C4 (Web Text))

Max Activating Token Index: 328

Text #2

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.7505. Min Act: -0.0002

Data Index: 452927 (C4 (Web Text))

Max Activating Token Index: 78

Text #3

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.7404. Min Act: -0.0002

Data Index: 623533 (C4 (Web Text))

Max Activating Token Index: 205

Text #4

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.7402. Min Act: -0.0002

Data Index: 25080 (C4 (Web Text))

Max Activating Token Index: 150

Text #5

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.7195. Min Act: -0.0002

Data Index: 1119480 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.7356. Min Act: -0.0002

Data Index: 1116443 (C4 (Web Text))

Max Activating Token Index: 205

Text #7

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.7258. Min Act: -0.0002

Data Index: 704566 (C4 (Web Text))

Max Activating Token Index: 612

Text #8

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.7177. Min Act: -0.0002

Data Index: 1238692 (C4 (Web Text))

Max Activating Token Index: 890

Text #9

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.6820. Min Act: -0.0002

Data Index: 1056325 (C4 (Web Text))

Max Activating Token Index: 81

Text #10

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.6868. Min Act: -0.0002

Data Index: 820879 (C4 (Web Text))

Max Activating Token Index: 184

Text #11

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.6902. Min Act: -0.0002

Data Index: 719406 (C4 (Web Text))

Max Activating Token Index: 316

Text #12

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.6714. Min Act: -0.0002

Data Index: 134180 (C4 (Web Text))

Max Activating Token Index: 267

Text #13

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.6692. Min Act: -0.0002

Data Index: 410738 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.6625. Min Act: -0.0002

Data Index: 1091432 (C4 (Web Text))

Max Activating Token Index: 125

Text #15

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.6803. Min Act: -0.0002

Data Index: 668581 (C4 (Web Text))

Max Activating Token Index: 656

Text #16

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.6768. Min Act: -0.0002

Data Index: 1349173 (C4 (Web Text))

Max Activating Token Index: 239

Text #17

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.6644. Min Act: -0.0003

Data Index: 838175 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.6728. Min Act: -0.0002

Data Index: 340653 (C4 (Web Text))

Max Activating Token Index: 214

Text #19

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.6745. Min Act: -0.0002

Data Index: 29475 (C4 (Web Text))

Max Activating Token Index: 43