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

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

Neuron 3819 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: 4.7974. Min Range: -4.7974

Max Act: 4.7735. Min Act: -0.0000

Data Index: 854409 (C4 (Web Text))

Max Activating Token Index: 30

Text #1

Max Range: 4.7974. Min Range: -4.7974

Max Act: 4.4391. Min Act: -0.0000

Data Index: 1343214 (C4 (Web Text))

Max Activating Token Index: 997

Text #2

Max Range: 4.7974. Min Range: -4.7974

Max Act: 4.7974. Min Act: -0.0000

Data Index: 592289 (C4 (Web Text))

Max Activating Token Index: 51

Text #3

Max Range: 4.7974. Min Range: -4.7974

Max Act: 4.3782. Min Act: -0.0000

Data Index: 422170 (C4 (Web Text))

Max Activating Token Index: 584

Text #4

Max Range: 4.7974. Min Range: -4.7974

Max Act: 4.5172. Min Act: -0.0000

Data Index: 228381 (C4 (Web Text))

Max Activating Token Index: 270

Text #5

Max Range: 4.7974. Min Range: -4.7974

Max Act: 4.5935. Min Act: -0.0000

Data Index: 737751 (C4 (Web Text))

Max Activating Token Index: 168

Text #6

Max Range: 4.7974. Min Range: -4.7974

Max Act: 4.5765. Min Act: -0.0000

Data Index: 239738 (C4 (Web Text))

Max Activating Token Index: 653

Text #7

Max Range: 4.7974. Min Range: -4.7974

Max Act: 4.3971. Min Act: -0.0000

Data Index: 1066978 (C4 (Web Text))

Max Activating Token Index: 688

Text #8

Max Range: 4.7974. Min Range: -4.7974

Max Act: 4.1711. Min Act: -0.0000

Data Index: 662568 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 4.7974. Min Range: -4.7974

Max Act: 3.9876. Min Act: -0.0000

Data Index: 958792 (C4 (Web Text))

Max Activating Token Index: 638

Text #10

Max Range: 4.7974. Min Range: -4.7974

Max Act: 3.9954. Min Act: -0.0000

Data Index: 257471 (C4 (Web Text))

Max Activating Token Index: 668

Text #11

Max Range: 4.7974. Min Range: -4.7974

Max Act: 3.8546. Min Act: -0.0000

Data Index: 431650 (C4 (Web Text))

Max Activating Token Index: 397

Text #12

Max Range: 4.7974. Min Range: -4.7974

Max Act: 3.9074. Min Act: -0.0000

Data Index: 31416 (C4 (Web Text))

Max Activating Token Index: 348

Text #13

Max Range: 4.7974. Min Range: -4.7974

Max Act: 4.0074. Min Act: -0.0000

Data Index: 1111351 (C4 (Web Text))

Max Activating Token Index: 490

Text #14

Max Range: 4.7974. Min Range: -4.7974

Max Act: 3.6224. Min Act: -0.0000

Data Index: 1088681 (C4 (Web Text))

Max Activating Token Index: 915

Text #15

Max Range: 4.7974. Min Range: -4.7974

Max Act: 3.5960. Min Act: -0.0000

Data Index: 633216 (C4 (Web Text))

Max Activating Token Index: 677

Text #16

Max Range: 4.7974. Min Range: -4.7974

Max Act: 3.8958. Min Act: -0.0000

Data Index: 1185661 (C4 (Web Text))

Max Activating Token Index: 685

Text #17

Max Range: 4.7974. Min Range: -4.7974

Max Act: 3.7033. Min Act: -0.0000

Data Index: 970663 (C4 (Web Text))

Max Activating Token Index: 162

Text #18

Max Range: 4.7974. Min Range: -4.7974

Max Act: 3.8475. Min Act: -0.0000

Data Index: 932225 (C4 (Web Text))

Max Activating Token Index: 937

Text #19

Max Range: 4.7974. Min Range: -4.7974

Max Act: 3.5596. Min Act: -0.0000

Data Index: 622017 (C4 (Web Text))

Max Activating Token Index: 564