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

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

Neuron 4627 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7427. Min Range: -1.7427

Max Act: 1.7427. Min Act: -0.0000

Data Index: 1207213 (C4 (Web Text))

Max Activating Token Index: 1014

Text #1

Max Range: 1.7427. Min Range: -1.7427

Max Act: 1.6105. Min Act: -0.0000

Data Index: 755580 (C4 (Web Text))

Max Activating Token Index: 975

Text #2

Max Range: 1.7427. Min Range: -1.7427

Max Act: 1.5283. Min Act: -0.0000

Data Index: 1170981 (C4 (Web Text))

Max Activating Token Index: 686

Text #3

Max Range: 1.7427. Min Range: -1.7427

Max Act: 1.2974. Min Act: -0.0000

Data Index: 1186708 (C4 (Web Text))

Max Activating Token Index: 283

Text #4

Max Range: 1.7427. Min Range: -1.7427

Max Act: 1.2662. Min Act: -0.0000

Data Index: 1460618 (Python Code)

Max Activating Token Index: 309

Text #5

Max Range: 1.7427. Min Range: -1.7427

Max Act: 1.1888. Min Act: -0.0000

Data Index: 957355 (C4 (Web Text))

Max Activating Token Index: 637

Text #6

Max Range: 1.7427. Min Range: -1.7427

Max Act: 1.1364. Min Act: -0.0000

Data Index: 55546 (C4 (Web Text))

Max Activating Token Index: 114

Text #7

Max Range: 1.7427. Min Range: -1.7427

Max Act: 1.1786. Min Act: -0.0000

Data Index: 485335 (C4 (Web Text))

Max Activating Token Index: 1004

Text #8

Max Range: 1.7427. Min Range: -1.7427

Max Act: 1.1963. Min Act: -0.0000

Data Index: 1501405 (Python Code)

Max Activating Token Index: 127

Text #9

Max Range: 1.7427. Min Range: -1.7427

Max Act: 0.9751. Min Act: -0.0000

Data Index: 1093134 (C4 (Web Text))

Max Activating Token Index: 778

Text #10

Max Range: 1.7427. Min Range: -1.7427

Max Act: 1.0554. Min Act: -0.0000

Data Index: 1485183 (Python Code)

Max Activating Token Index: 799

Text #11

Max Range: 1.7427. Min Range: -1.7427

Max Act: 1.0185. Min Act: -0.0000

Data Index: 987827 (C4 (Web Text))

Max Activating Token Index: 850

Text #12

Max Range: 1.7427. Min Range: -1.7427

Max Act: 1.0101. Min Act: -0.0000

Data Index: 1364537 (Python Code)

Max Activating Token Index: 97

Text #13

Max Range: 1.7427. Min Range: -1.7427

Max Act: 1.0249. Min Act: -0.0000

Data Index: 1419467 (Python Code)

Max Activating Token Index: 684

Text #14

Max Range: 1.7427. Min Range: -1.7427

Max Act: 1.0433. Min Act: -0.0000

Data Index: 361633 (C4 (Web Text))

Max Activating Token Index: 163

Text #15

Max Range: 1.7427. Min Range: -1.7427

Max Act: 0.9445. Min Act: -0.0000

Data Index: 1559610 (Python Code)

Max Activating Token Index: 552

Text #16

Max Range: 1.7427. Min Range: -1.7427

Max Act: 1.0347. Min Act: -0.0000

Data Index: 618281 (C4 (Web Text))

Max Activating Token Index: 756

Text #17

Max Range: 1.7427. Min Range: -1.7427

Max Act: 0.9000. Min Act: -0.0000

Data Index: 856039 (C4 (Web Text))

Max Activating Token Index: 885

Text #18

Max Range: 1.7427. Min Range: -1.7427

Max Act: 0.9307. Min Act: -0.0000

Data Index: 705099 (C4 (Web Text))

Max Activating Token Index: 611

Text #19

Max Range: 1.7427. Min Range: -1.7427

Max Act: 0.9018. Min Act: -0.0000

Data Index: 1646060 (Python Code)

Max Activating Token Index: 167