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

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

Neuron 3387 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8714. Min Range: -2.8714

Max Act: 2.8714. Min Act: -0.0000

Data Index: 947073 (C4 (Web Text))

Max Activating Token Index: 7

Text #1

Max Range: 2.8714. Min Range: -2.8714

Max Act: 2.6967. Min Act: -0.0000

Data Index: 499538 (C4 (Web Text))

Max Activating Token Index: 40

Text #2

Max Range: 2.8714. Min Range: -2.8714

Max Act: 2.4447. Min Act: -0.0000

Data Index: 1500452 (Python Code)

Max Activating Token Index: 220

Text #3

Max Range: 2.8714. Min Range: -2.8714

Max Act: 2.3086. Min Act: -0.0000

Data Index: 1425046 (Python Code)

Max Activating Token Index: 823

Text #4

Max Range: 2.8714. Min Range: -2.8714

Max Act: 2.3905. Min Act: -0.0000

Data Index: 1256517 (C4 (Web Text))

Max Activating Token Index: 122

Text #5

Max Range: 2.8714. Min Range: -2.8714

Max Act: 2.1913. Min Act: -0.0000

Data Index: 193673 (C4 (Web Text))

Max Activating Token Index: 367

Text #6

Max Range: 2.8714. Min Range: -2.8714

Max Act: 2.2161. Min Act: -0.0000

Data Index: 1111682 (C4 (Web Text))

Max Activating Token Index: 740

Text #7

Max Range: 2.8714. Min Range: -2.8714

Max Act: 2.3207. Min Act: -0.0000

Data Index: 1255611 (C4 (Web Text))

Max Activating Token Index: 360

Text #8

Max Range: 2.8714. Min Range: -2.8714

Max Act: 2.2917. Min Act: -0.0000

Data Index: 376933 (C4 (Web Text))

Max Activating Token Index: 471

Text #9

Max Range: 2.8714. Min Range: -2.8714

Max Act: 2.2808. Min Act: -0.0000

Data Index: 53589 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 2.8714. Min Range: -2.8714

Max Act: 2.2733. Min Act: -0.0000

Data Index: 1247733 (C4 (Web Text))

Max Activating Token Index: 727

Text #11

Max Range: 2.8714. Min Range: -2.8714

Max Act: 2.2715. Min Act: -0.0000

Data Index: 488581 (C4 (Web Text))

Max Activating Token Index: 562

Text #12

Max Range: 2.8714. Min Range: -2.8714

Max Act: 2.2570. Min Act: -0.0000

Data Index: 714154 (C4 (Web Text))

Max Activating Token Index: 94

Text #13

Max Range: 2.8714. Min Range: -2.8714

Max Act: 2.1619. Min Act: -0.0000

Data Index: 8793 (C4 (Web Text))

Max Activating Token Index: 434

Text #14

Max Range: 2.8714. Min Range: -2.8714

Max Act: 2.2514. Min Act: -0.0000

Data Index: 219876 (C4 (Web Text))

Max Activating Token Index: 603

Text #15

Max Range: 2.8714. Min Range: -2.8714

Max Act: 2.2475. Min Act: -0.0000

Data Index: 1047660 (C4 (Web Text))

Max Activating Token Index: 552

Text #16

Max Range: 2.8714. Min Range: -2.8714

Max Act: 2.2118. Min Act: -0.0000

Data Index: 1322659 (C4 (Web Text))

Max Activating Token Index: 707

Text #17

Max Range: 2.8714. Min Range: -2.8714

Max Act: 2.0938. Min Act: -0.0000

Data Index: 498221 (C4 (Web Text))

Max Activating Token Index: 672

Text #18

Max Range: 2.8714. Min Range: -2.8714

Max Act: 2.1745. Min Act: -0.0000

Data Index: 80590 (C4 (Web Text))

Max Activating Token Index: 708

Text #19

Max Range: 2.8714. Min Range: -2.8714

Max Act: 2.1792. Min Act: -0.0000

Data Index: 1030717 (C4 (Web Text))

Max Activating Token Index: 543