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

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

Neuron 4818 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9210. Min Range: -2.9210

Max Act: 2.9210. Min Act: -0.0000

Data Index: 58679 (C4 (Web Text))

Max Activating Token Index: 687

Text #1

Max Range: 2.9210. Min Range: -2.9210

Max Act: 2.3718. Min Act: -0.0000

Data Index: 555744 (C4 (Web Text))

Max Activating Token Index: 65

Text #2

Max Range: 2.9210. Min Range: -2.9210

Max Act: 2.3487. Min Act: -0.0000

Data Index: 310860 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 2.9210. Min Range: -2.9210

Max Act: 2.2488. Min Act: -0.0000

Data Index: 765506 (C4 (Web Text))

Max Activating Token Index: 596

Text #4

Max Range: 2.9210. Min Range: -2.9210

Max Act: 2.1798. Min Act: -0.0000

Data Index: 1350441 (C4 (Web Text))

Max Activating Token Index: 122

Text #5

Max Range: 2.9210. Min Range: -2.9210

Max Act: 2.1597. Min Act: -0.0000

Data Index: 352454 (C4 (Web Text))

Max Activating Token Index: 904

Text #6

Max Range: 2.9210. Min Range: -2.9210

Max Act: 2.1468. Min Act: 0.0000

Data Index: 152379 (C4 (Web Text))

Max Activating Token Index: 876

Text #7

Max Range: 2.9210. Min Range: -2.9210

Max Act: 2.0535. Min Act: -0.0000

Data Index: 644363 (C4 (Web Text))

Max Activating Token Index: 892

Text #8

Max Range: 2.9210. Min Range: -2.9210

Max Act: 2.1777. Min Act: -0.0000

Data Index: 1121434 (C4 (Web Text))

Max Activating Token Index: 721

Text #9

Max Range: 2.9210. Min Range: -2.9210

Max Act: 2.0472. Min Act: -0.0000

Data Index: 376477 (C4 (Web Text))

Max Activating Token Index: 158

Text #10

Max Range: 2.9210. Min Range: -2.9210

Max Act: 1.9074. Min Act: -0.0000

Data Index: 877320 (C4 (Web Text))

Max Activating Token Index: 117

Text #11

Max Range: 2.9210. Min Range: -2.9210

Max Act: 2.0962. Min Act: -0.0000

Data Index: 295807 (C4 (Web Text))

Max Activating Token Index: 971

Text #12

Max Range: 2.9210. Min Range: -2.9210

Max Act: 1.9347. Min Act: -0.0000

Data Index: 1257530 (C4 (Web Text))

Max Activating Token Index: 922

Text #13

Max Range: 2.9210. Min Range: -2.9210

Max Act: 1.9333. Min Act: -0.0000

Data Index: 799072 (C4 (Web Text))

Max Activating Token Index: 39

Text #14

Max Range: 2.9210. Min Range: -2.9210

Max Act: 1.9319. Min Act: -0.0000

Data Index: 69605 (C4 (Web Text))

Max Activating Token Index: 172

Text #15

Max Range: 2.9210. Min Range: -2.9210

Max Act: 2.0234. Min Act: -0.0000

Data Index: 756391 (C4 (Web Text))

Max Activating Token Index: 765

Text #16

Max Range: 2.9210. Min Range: -2.9210

Max Act: 1.9100. Min Act: -0.0000

Data Index: 1332739 (C4 (Web Text))

Max Activating Token Index: 87

Text #17

Max Range: 2.9210. Min Range: -2.9210

Max Act: 1.9264. Min Act: -0.0000

Data Index: 1187666 (C4 (Web Text))

Max Activating Token Index: 296

Text #18

Max Range: 2.9210. Min Range: -2.9210

Max Act: 1.7920. Min Act: -0.0000

Data Index: 879748 (C4 (Web Text))

Max Activating Token Index: 853

Text #19

Max Range: 2.9210. Min Range: -2.9210

Max Act: 1.8733. Min Act: -0.0000

Data Index: 769679 (C4 (Web Text))

Max Activating Token Index: 679