Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3751 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5800. Min Range: -0.5800

Max Act: 0.4859. Min Act: -0.0001

Data Index: 841111 (C4 (Web Text))

Max Activating Token Index: 752

Text #1

Max Range: 0.5800. Min Range: -0.5800

Max Act: 0.5710. Min Act: -0.0000

Data Index: 1468743 (Python Code)

Max Activating Token Index: 63

Text #2

Max Range: 0.5800. Min Range: -0.5800

Max Act: 0.5666. Min Act: -0.0000

Data Index: 1388695 (Python Code)

Max Activating Token Index: 24

Text #3

Max Range: 0.5800. Min Range: -0.5800

Max Act: 0.5679. Min Act: -0.0001

Data Index: 1345118 (C4 (Web Text))

Max Activating Token Index: 433

Text #4

Max Range: 0.5800. Min Range: -0.5800

Max Act: 0.5420. Min Act: -0.0000

Data Index: 1364347 (Python Code)

Max Activating Token Index: 27

Text #5

Max Range: 0.5800. Min Range: -0.5800

Max Act: 0.5800. Min Act: -0.0001

Data Index: 911589 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 0.5800. Min Range: -0.5800

Max Act: 0.5316. Min Act: -0.0000

Data Index: 679757 (C4 (Web Text))

Max Activating Token Index: 667

Text #7

Max Range: 0.5800. Min Range: -0.5800

Max Act: 0.5466. Min Act: -0.0001

Data Index: 1554689 (Python Code)

Max Activating Token Index: 122

Text #8

Max Range: 0.5800. Min Range: -0.5800

Max Act: 0.5425. Min Act: -0.0001

Data Index: 1356736 (C4 (Web Text))

Max Activating Token Index: 719

Text #9

Max Range: 0.5800. Min Range: -0.5800

Max Act: 0.5335. Min Act: -0.0001

Data Index: 1381622 (Python Code)

Max Activating Token Index: 115

Text #10

Max Range: 0.5800. Min Range: -0.5800

Max Act: 0.5424. Min Act: -0.0001

Data Index: 1634893 (Python Code)

Max Activating Token Index: 61

Text #11

Max Range: 0.5800. Min Range: -0.5800

Max Act: 0.5438. Min Act: -0.0000

Data Index: 1648717 (Python Code)

Max Activating Token Index: 83

Text #12

Max Range: 0.5800. Min Range: -0.5800

Max Act: 0.5012. Min Act: -0.0000

Data Index: 1494834 (Python Code)

Max Activating Token Index: 157

Text #13

Max Range: 0.5800. Min Range: -0.5800

Max Act: 0.5544. Min Act: -0.0000

Data Index: 1650883 (Python Code)

Max Activating Token Index: 158

Text #14

Max Range: 0.5800. Min Range: -0.5800

Max Act: 0.5389. Min Act: -0.0000

Data Index: 1434528 (Python Code)

Max Activating Token Index: 472

Text #15

Max Range: 0.5800. Min Range: -0.5800

Max Act: 0.5365. Min Act: -0.0000

Data Index: 1434597 (Python Code)

Max Activating Token Index: 393

Text #16

Max Range: 0.5800. Min Range: -0.5800

Max Act: 0.5547. Min Act: -0.0001

Data Index: 586311 (C4 (Web Text))

Max Activating Token Index: 257

Text #17

Max Range: 0.5800. Min Range: -0.5800

Max Act: 0.5190. Min Act: -0.0000

Data Index: 1543946 (Python Code)

Max Activating Token Index: 16

Text #18

Max Range: 0.5800. Min Range: -0.5800

Max Act: 0.5145. Min Act: -0.0001

Data Index: 265631 (C4 (Web Text))

Max Activating Token Index: 999

Text #19

Max Range: 0.5800. Min Range: -0.5800

Max Act: 0.5362. Min Act: -0.0000

Data Index: 1579545 (Python Code)

Max Activating Token Index: 97