Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1975 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3217. Min Range: -0.3217

Max Act: 0.3217. Min Act: -0.0000

Data Index: 577681 (C4 (Web Text))

Max Activating Token Index: 170

Text #1

Max Range: 0.3217. Min Range: -0.3217

Max Act: 0.3119. Min Act: -0.0000

Data Index: 817295 (C4 (Web Text))

Max Activating Token Index: 223

Text #2

Max Range: 0.3217. Min Range: -0.3217

Max Act: 0.3048. Min Act: -0.0000

Data Index: 505083 (C4 (Web Text))

Max Activating Token Index: 465

Text #3

Max Range: 0.3217. Min Range: -0.3217

Max Act: 0.3033. Min Act: -0.0000

Data Index: 651416 (C4 (Web Text))

Max Activating Token Index: 462

Text #4

Max Range: 0.3217. Min Range: -0.3217

Max Act: 0.3005. Min Act: -0.0000

Data Index: 411526 (C4 (Web Text))

Max Activating Token Index: 189

Text #5

Max Range: 0.3217. Min Range: -0.3217

Max Act: 0.2972. Min Act: -0.0000

Data Index: 353693 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 0.3217. Min Range: -0.3217

Max Act: 0.3018. Min Act: -0.0000

Data Index: 412995 (C4 (Web Text))

Max Activating Token Index: 529

Text #7

Max Range: 0.3217. Min Range: -0.3217

Max Act: 0.2906. Min Act: -0.0000

Data Index: 26592 (C4 (Web Text))

Max Activating Token Index: 697

Text #8

Max Range: 0.3217. Min Range: -0.3217

Max Act: 0.2912. Min Act: -0.0000

Data Index: 839666 (C4 (Web Text))

Max Activating Token Index: 755

Text #9

Max Range: 0.3217. Min Range: -0.3217

Max Act: 0.2922. Min Act: -0.0000

Data Index: 1133702 (C4 (Web Text))

Max Activating Token Index: 413

Text #10

Max Range: 0.3217. Min Range: -0.3217

Max Act: 0.2815. Min Act: -0.0000

Data Index: 1109374 (C4 (Web Text))

Max Activating Token Index: 1013

Text #11

Max Range: 0.3217. Min Range: -0.3217

Max Act: 0.2786. Min Act: -0.0000

Data Index: 40211 (C4 (Web Text))

Max Activating Token Index: 256

Text #12

Max Range: 0.3217. Min Range: -0.3217

Max Act: 0.2721. Min Act: -0.0000

Data Index: 136759 (C4 (Web Text))

Max Activating Token Index: 348

Text #13

Max Range: 0.3217. Min Range: -0.3217

Max Act: 0.2712. Min Act: -0.0000

Data Index: 100077 (C4 (Web Text))

Max Activating Token Index: 239

Text #14

Max Range: 0.3217. Min Range: -0.3217

Max Act: 0.2698. Min Act: -0.0000

Data Index: 653245 (C4 (Web Text))

Max Activating Token Index: 311

Text #15

Max Range: 0.3217. Min Range: -0.3217

Max Act: 0.2689. Min Act: -0.0000

Data Index: 453140 (C4 (Web Text))

Max Activating Token Index: 97

Text #16

Max Range: 0.3217. Min Range: -0.3217

Max Act: 0.2678. Min Act: -0.0000

Data Index: 850935 (C4 (Web Text))

Max Activating Token Index: 727

Text #17

Max Range: 0.3217. Min Range: -0.3217

Max Act: 0.2667. Min Act: -0.0000

Data Index: 1115779 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 0.3217. Min Range: -0.3217

Max Act: 0.2666. Min Act: -0.0000

Data Index: 110098 (C4 (Web Text))

Max Activating Token Index: 315

Text #19

Max Range: 0.3217. Min Range: -0.3217

Max Act: 0.2577. Min Act: -0.0000

Data Index: 270723 (C4 (Web Text))

Max Activating Token Index: 323