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

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

Neuron 2321 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: 0.8582. Min Range: -0.8582

Max Act: 0.8582. Min Act: -0.0000

Data Index: 957217 (C4 (Web Text))

Max Activating Token Index: 124

Text #1

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.8496. Min Act: -0.0000

Data Index: 611948 (C4 (Web Text))

Max Activating Token Index: 626

Text #2

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.7771. Min Act: -0.0000

Data Index: 1120110 (C4 (Web Text))

Max Activating Token Index: 341

Text #3

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.7767. Min Act: -0.0000

Data Index: 716890 (C4 (Web Text))

Max Activating Token Index: 169

Text #4

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.7219. Min Act: -0.0000

Data Index: 631089 (C4 (Web Text))

Max Activating Token Index: 769

Text #5

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.7539. Min Act: -0.0000

Data Index: 716331 (C4 (Web Text))

Max Activating Token Index: 619

Text #6

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.6526. Min Act: -0.0000

Data Index: 1458196 (Python Code)

Max Activating Token Index: 71

Text #7

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.5989. Min Act: -0.0000

Data Index: 207971 (C4 (Web Text))

Max Activating Token Index: 82

Text #8

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.6320. Min Act: -0.0000

Data Index: 358287 (C4 (Web Text))

Max Activating Token Index: 146

Text #9

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.5955. Min Act: -0.0000

Data Index: 69333 (C4 (Web Text))

Max Activating Token Index: 284

Text #10

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.6089. Min Act: -0.0000

Data Index: 428199 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.6504. Min Act: -0.0000

Data Index: 170441 (C4 (Web Text))

Max Activating Token Index: 737

Text #12

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.5685. Min Act: -0.0000

Data Index: 1203377 (C4 (Web Text))

Max Activating Token Index: 188

Text #13

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.5809. Min Act: -0.0000

Data Index: 392258 (C4 (Web Text))

Max Activating Token Index: 120

Text #14

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.6112. Min Act: -0.0000

Data Index: 128031 (C4 (Web Text))

Max Activating Token Index: 533

Text #15

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.5699. Min Act: -0.0000

Data Index: 1391595 (Python Code)

Max Activating Token Index: 110

Text #16

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.5030. Min Act: -0.0000

Data Index: 626285 (C4 (Web Text))

Max Activating Token Index: 999

Text #17

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.5031. Min Act: -0.0000

Data Index: 571590 (C4 (Web Text))

Max Activating Token Index: 329

Text #18

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.5243. Min Act: -0.0000

Data Index: 1633266 (Python Code)

Max Activating Token Index: 214

Text #19

Max Range: 0.8582. Min Range: -0.8582

Max Act: 0.5080. Min Act: -0.0000

Data Index: 1578978 (Python Code)

Max Activating Token Index: 630