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

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

Neuron 244 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7954. Min Range: -1.7954

Max Act: 1.7932. Min Act: -0.0001

Data Index: 488393 (C4 (Web Text))

Max Activating Token Index: 538

Text #1

Max Range: 1.7954. Min Range: -1.7954

Max Act: 1.7954. Min Act: -0.0001

Data Index: 404255 (C4 (Web Text))

Max Activating Token Index: 673

Text #2

Max Range: 1.7954. Min Range: -1.7954

Max Act: 1.5960. Min Act: -0.0001

Data Index: 893965 (C4 (Web Text))

Max Activating Token Index: 605

Text #3

Max Range: 1.7954. Min Range: -1.7954

Max Act: 1.5415. Min Act: -0.0001

Data Index: 1211024 (C4 (Web Text))

Max Activating Token Index: 465

Text #4

Max Range: 1.7954. Min Range: -1.7954

Max Act: 1.4001. Min Act: -0.0001

Data Index: 52209 (C4 (Web Text))

Max Activating Token Index: 451

Text #5

Max Range: 1.7954. Min Range: -1.7954

Max Act: 1.3445. Min Act: -0.0001

Data Index: 1220256 (C4 (Web Text))

Max Activating Token Index: 733

Text #6

Max Range: 1.7954. Min Range: -1.7954

Max Act: 1.2700. Min Act: -0.0001

Data Index: 558199 (C4 (Web Text))

Max Activating Token Index: 136

Text #7

Max Range: 1.7954. Min Range: -1.7954

Max Act: 1.2954. Min Act: -0.0001

Data Index: 20082 (C4 (Web Text))

Max Activating Token Index: 344

Text #8

Max Range: 1.7954. Min Range: -1.7954

Max Act: 1.2217. Min Act: -0.0001

Data Index: 1325182 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 1.7954. Min Range: -1.7954

Max Act: 1.1412. Min Act: -0.0001

Data Index: 644478 (C4 (Web Text))

Max Activating Token Index: 883

Text #10

Max Range: 1.7954. Min Range: -1.7954

Max Act: 1.1976. Min Act: -0.0001

Data Index: 397227 (C4 (Web Text))

Max Activating Token Index: 157

Text #11

Max Range: 1.7954. Min Range: -1.7954

Max Act: 1.0159. Min Act: -0.0001

Data Index: 973979 (C4 (Web Text))

Max Activating Token Index: 734

Text #12

Max Range: 1.7954. Min Range: -1.7954

Max Act: 1.0387. Min Act: -0.0001

Data Index: 848060 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 1.7954. Min Range: -1.7954

Max Act: 1.0738. Min Act: -0.0001

Data Index: 1318784 (C4 (Web Text))

Max Activating Token Index: 8

Text #14

Max Range: 1.7954. Min Range: -1.7954

Max Act: 0.9698. Min Act: -0.0001

Data Index: 152735 (C4 (Web Text))

Max Activating Token Index: 101

Text #15

Max Range: 1.7954. Min Range: -1.7954

Max Act: 0.9723. Min Act: -0.0001

Data Index: 1323579 (C4 (Web Text))

Max Activating Token Index: 90

Text #16

Max Range: 1.7954. Min Range: -1.7954

Max Act: 0.9832. Min Act: -0.0001

Data Index: 1055898 (C4 (Web Text))

Max Activating Token Index: 123

Text #17

Max Range: 1.7954. Min Range: -1.7954

Max Act: 1.0138. Min Act: -0.0001

Data Index: 727169 (C4 (Web Text))

Max Activating Token Index: 492

Text #18

Max Range: 1.7954. Min Range: -1.7954

Max Act: 1.0414. Min Act: -0.0001

Data Index: 184983 (C4 (Web Text))

Max Activating Token Index: 972

Text #19

Max Range: 1.7954. Min Range: -1.7954

Max Act: 1.0028. Min Act: -0.0001

Data Index: 289300 (C4 (Web Text))

Max Activating Token Index: 215