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

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

Neuron 1211 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: 0.2441. Min Range: -0.2441

Max Act: 0.2441. Min Act: -0.0000

Data Index: 842103 (C4 (Web Text))

Max Activating Token Index: 986

Text #1

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.2413. Min Act: -0.0000

Data Index: 1219743 (C4 (Web Text))

Max Activating Token Index: 523

Text #2

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.2079. Min Act: -0.0000

Data Index: 1034936 (C4 (Web Text))

Max Activating Token Index: 404

Text #3

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.1991. Min Act: -0.0000

Data Index: 1074609 (C4 (Web Text))

Max Activating Token Index: 435

Text #4

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.2039. Min Act: -0.0000

Data Index: 538468 (C4 (Web Text))

Max Activating Token Index: 374

Text #5

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.2017. Min Act: -0.0000

Data Index: 1509950 (Python Code)

Max Activating Token Index: 21

Text #6

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.2047. Min Act: -0.0000

Data Index: 514864 (C4 (Web Text))

Max Activating Token Index: 608

Text #7

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.2053. Min Act: -0.0000

Data Index: 1321740 (C4 (Web Text))

Max Activating Token Index: 635

Text #8

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.1921. Min Act: -0.0000

Data Index: 54982 (C4 (Web Text))

Max Activating Token Index: 16

Text #9

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.1911. Min Act: -0.0000

Data Index: 1349342 (C4 (Web Text))

Max Activating Token Index: 842

Text #10

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.1837. Min Act: -0.0000

Data Index: 1284730 (C4 (Web Text))

Max Activating Token Index: 54

Text #11

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.1851. Min Act: -0.0000

Data Index: 1264619 (C4 (Web Text))

Max Activating Token Index: 455

Text #12

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.1878. Min Act: -0.0000

Data Index: 474138 (C4 (Web Text))

Max Activating Token Index: 657

Text #13

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.1743. Min Act: -0.0000

Data Index: 1245161 (C4 (Web Text))

Max Activating Token Index: 498

Text #14

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.1775. Min Act: -0.0000

Data Index: 387288 (C4 (Web Text))

Max Activating Token Index: 270

Text #15

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.1815. Min Act: -0.0000

Data Index: 18026 (C4 (Web Text))

Max Activating Token Index: 200

Text #16

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.1704. Min Act: -0.0000

Data Index: 827586 (C4 (Web Text))

Max Activating Token Index: 651

Text #17

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.1806. Min Act: -0.0000

Data Index: 119039 (C4 (Web Text))

Max Activating Token Index: 255

Text #18

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.1691. Min Act: -0.0000

Data Index: 273589 (C4 (Web Text))

Max Activating Token Index: 202

Text #19

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.1787. Min Act: -0.0000

Data Index: 275384 (C4 (Web Text))

Max Activating Token Index: 619