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

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

Neuron 4818 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1501. Min Range: -2.1501

Max Act: 2.1501. Min Act: -0.0000

Data Index: 52483 (C4 (Web Text))

Max Activating Token Index: 793

Text #1

Max Range: 2.1501. Min Range: -2.1501

Max Act: 1.7946. Min Act: -0.0000

Data Index: 816512 (C4 (Web Text))

Max Activating Token Index: 505

Text #2

Max Range: 2.1501. Min Range: -2.1501

Max Act: 1.9019. Min Act: -0.0000

Data Index: 802034 (C4 (Web Text))

Max Activating Token Index: 978

Text #3

Max Range: 2.1501. Min Range: -2.1501

Max Act: 1.7844. Min Act: -0.0000

Data Index: 1184672 (C4 (Web Text))

Max Activating Token Index: 965

Text #4

Max Range: 2.1501. Min Range: -2.1501

Max Act: 1.7768. Min Act: -0.0000

Data Index: 521605 (C4 (Web Text))

Max Activating Token Index: 373

Text #5

Max Range: 2.1501. Min Range: -2.1501

Max Act: 1.7316. Min Act: -0.0000

Data Index: 603219 (C4 (Web Text))

Max Activating Token Index: 105

Text #6

Max Range: 2.1501. Min Range: -2.1501

Max Act: 1.7066. Min Act: -0.0000

Data Index: 1111013 (C4 (Web Text))

Max Activating Token Index: 573

Text #7

Max Range: 2.1501. Min Range: -2.1501

Max Act: 1.7020. Min Act: -0.0000

Data Index: 555812 (C4 (Web Text))

Max Activating Token Index: 694

Text #8

Max Range: 2.1501. Min Range: -2.1501

Max Act: 1.6538. Min Act: -0.0000

Data Index: 1091116 (C4 (Web Text))

Max Activating Token Index: 620

Text #9

Max Range: 2.1501. Min Range: -2.1501

Max Act: 1.6348. Min Act: -0.0000

Data Index: 543189 (C4 (Web Text))

Max Activating Token Index: 820

Text #10

Max Range: 2.1501. Min Range: -2.1501

Max Act: 1.6071. Min Act: -0.0000

Data Index: 602102 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 2.1501. Min Range: -2.1501

Max Act: 1.6814. Min Act: -0.0000

Data Index: 184947 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 2.1501. Min Range: -2.1501

Max Act: 1.5639. Min Act: -0.0000

Data Index: 160714 (C4 (Web Text))

Max Activating Token Index: 39

Text #13

Max Range: 2.1501. Min Range: -2.1501

Max Act: 1.5461. Min Act: -0.0000

Data Index: 1347121 (C4 (Web Text))

Max Activating Token Index: 152

Text #14

Max Range: 2.1501. Min Range: -2.1501

Max Act: 1.5403. Min Act: -0.0000

Data Index: 304920 (C4 (Web Text))

Max Activating Token Index: 485

Text #15

Max Range: 2.1501. Min Range: -2.1501

Max Act: 1.5349. Min Act: -0.0000

Data Index: 716010 (C4 (Web Text))

Max Activating Token Index: 204

Text #16

Max Range: 2.1501. Min Range: -2.1501

Max Act: 1.5355. Min Act: -0.0000

Data Index: 883708 (C4 (Web Text))

Max Activating Token Index: 941

Text #17

Max Range: 2.1501. Min Range: -2.1501

Max Act: 1.5206. Min Act: -0.0000

Data Index: 131390 (C4 (Web Text))

Max Activating Token Index: 465

Text #18

Max Range: 2.1501. Min Range: -2.1501

Max Act: 1.4774. Min Act: -0.0000

Data Index: 707744 (C4 (Web Text))

Max Activating Token Index: 896

Text #19

Max Range: 2.1501. Min Range: -2.1501

Max Act: 1.5009. Min Act: -0.0000

Data Index: 57806 (C4 (Web Text))

Max Activating Token Index: 141