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

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

Neuron 3166 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4842. Min Range: -2.4842

Max Act: 2.4842. Min Act: 0.0000

Data Index: 1060495 (C4 (Web Text))

Max Activating Token Index: 92

Text #1

Max Range: 2.4842. Min Range: -2.4842

Max Act: 2.2578. Min Act: -0.0000

Data Index: 764106 (C4 (Web Text))

Max Activating Token Index: 722

Text #2

Max Range: 2.4842. Min Range: -2.4842

Max Act: 1.7775. Min Act: -0.0000

Data Index: 986060 (C4 (Web Text))

Max Activating Token Index: 128

Text #3

Max Range: 2.4842. Min Range: -2.4842

Max Act: 1.7799. Min Act: -0.0000

Data Index: 1168411 (C4 (Web Text))

Max Activating Token Index: 151

Text #4

Max Range: 2.4842. Min Range: -2.4842

Max Act: 1.6526. Min Act: -0.0000

Data Index: 73864 (C4 (Web Text))

Max Activating Token Index: 168

Text #5

Max Range: 2.4842. Min Range: -2.4842

Max Act: 1.7314. Min Act: 0.0000

Data Index: 142981 (C4 (Web Text))

Max Activating Token Index: 861

Text #6

Max Range: 2.4842. Min Range: -2.4842

Max Act: 1.6752. Min Act: -0.0000

Data Index: 1471302 (Python Code)

Max Activating Token Index: 644

Text #7

Max Range: 2.4842. Min Range: -2.4842

Max Act: 1.5210. Min Act: -0.0000

Data Index: 321885 (C4 (Web Text))

Max Activating Token Index: 225

Text #8

Max Range: 2.4842. Min Range: -2.4842

Max Act: 1.6352. Min Act: -0.0000

Data Index: 1182456 (C4 (Web Text))

Max Activating Token Index: 144

Text #9

Max Range: 2.4842. Min Range: -2.4842

Max Act: 1.4035. Min Act: 0.0000

Data Index: 189486 (C4 (Web Text))

Max Activating Token Index: 580

Text #10

Max Range: 2.4842. Min Range: -2.4842

Max Act: 1.3341. Min Act: -0.0000

Data Index: 1014480 (C4 (Web Text))

Max Activating Token Index: 389

Text #11

Max Range: 2.4842. Min Range: -2.4842

Max Act: 1.5671. Min Act: -0.0000

Data Index: 141509 (C4 (Web Text))

Max Activating Token Index: 673

Text #12

Max Range: 2.4842. Min Range: -2.4842

Max Act: 1.6557. Min Act: -0.0000

Data Index: 601978 (C4 (Web Text))

Max Activating Token Index: 570

Text #13

Max Range: 2.4842. Min Range: -2.4842

Max Act: 1.3096. Min Act: -0.0000

Data Index: 867737 (C4 (Web Text))

Max Activating Token Index: 761

Text #14

Max Range: 2.4842. Min Range: -2.4842

Max Act: 1.2936. Min Act: -0.0000

Data Index: 449127 (C4 (Web Text))

Max Activating Token Index: 757

Text #15

Max Range: 2.4842. Min Range: -2.4842

Max Act: 1.2926. Min Act: 0.0000

Data Index: 442132 (C4 (Web Text))

Max Activating Token Index: 715

Text #16

Max Range: 2.4842. Min Range: -2.4842

Max Act: 1.4691. Min Act: -0.0000

Data Index: 443416 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 2.4842. Min Range: -2.4842

Max Act: 1.4558. Min Act: -0.0000

Data Index: 670426 (C4 (Web Text))

Max Activating Token Index: 258

Text #18

Max Range: 2.4842. Min Range: -2.4842

Max Act: 1.4365. Min Act: 0.0000

Data Index: 807460 (C4 (Web Text))

Max Activating Token Index: 712

Text #19

Max Range: 2.4842. Min Range: -2.4842

Max Act: 1.4349. Min Act: -0.0000

Data Index: 816726 (C4 (Web Text))

Max Activating Token Index: 864