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

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

Neuron 1140 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3791. Min Range: -4.3791

Max Act: 4.3791. Min Act: -0.0000

Data Index: 1520630 (Python Code)

Max Activating Token Index: 404

Text #1

Max Range: 4.3791. Min Range: -4.3791

Max Act: 3.6527. Min Act: -0.0001

Data Index: 1389858 (Python Code)

Max Activating Token Index: 620

Text #2

Max Range: 4.3791. Min Range: -4.3791

Max Act: 3.0763. Min Act: -0.0001

Data Index: 1643308 (Python Code)

Max Activating Token Index: 393

Text #3

Max Range: 4.3791. Min Range: -4.3791

Max Act: 2.7294. Min Act: -0.0000

Data Index: 1485531 (Python Code)

Max Activating Token Index: 355

Text #4

Max Range: 4.3791. Min Range: -4.3791

Max Act: 2.8324. Min Act: -0.0000

Data Index: 1436674 (Python Code)

Max Activating Token Index: 260

Text #5

Max Range: 4.3791. Min Range: -4.3791

Max Act: 2.6198. Min Act: -0.0000

Data Index: 1483187 (Python Code)

Max Activating Token Index: 83

Text #6

Max Range: 4.3791. Min Range: -4.3791

Max Act: 2.7268. Min Act: -0.0000

Data Index: 1389057 (Python Code)

Max Activating Token Index: 225

Text #7

Max Range: 4.3791. Min Range: -4.3791

Max Act: 2.5629. Min Act: -0.0000

Data Index: 1629353 (Python Code)

Max Activating Token Index: 156

Text #8

Max Range: 4.3791. Min Range: -4.3791

Max Act: 2.5248. Min Act: -0.0000

Data Index: 1641448 (Python Code)

Max Activating Token Index: 187

Text #9

Max Range: 4.3791. Min Range: -4.3791

Max Act: 2.6497. Min Act: -0.0000

Data Index: 1526099 (Python Code)

Max Activating Token Index: 149

Text #10

Max Range: 4.3791. Min Range: -4.3791

Max Act: 2.6112. Min Act: -0.0000

Data Index: 1491128 (Python Code)

Max Activating Token Index: 99

Text #11

Max Range: 4.3791. Min Range: -4.3791

Max Act: 2.4111. Min Act: -0.0000

Data Index: 1650125 (Python Code)

Max Activating Token Index: 830

Text #12

Max Range: 4.3791. Min Range: -4.3791

Max Act: 2.4968. Min Act: -0.0001

Data Index: 1603610 (Python Code)

Max Activating Token Index: 474

Text #13

Max Range: 4.3791. Min Range: -4.3791

Max Act: 2.6222. Min Act: -0.0000

Data Index: 1557022 (Python Code)

Max Activating Token Index: 479

Text #14

Max Range: 4.3791. Min Range: -4.3791

Max Act: 2.4914. Min Act: -0.0000

Data Index: 1639813 (Python Code)

Max Activating Token Index: 143

Text #15

Max Range: 4.3791. Min Range: -4.3791

Max Act: 2.4783. Min Act: -0.0000

Data Index: 1590546 (Python Code)

Max Activating Token Index: 35

Text #16

Max Range: 4.3791. Min Range: -4.3791

Max Act: 2.4615. Min Act: -0.0001

Data Index: 1643227 (Python Code)

Max Activating Token Index: 797

Text #17

Max Range: 4.3791. Min Range: -4.3791

Max Act: 2.7181. Min Act: -0.0000

Data Index: 1586700 (Python Code)

Max Activating Token Index: 89

Text #18

Max Range: 4.3791. Min Range: -4.3791

Max Act: 2.5851. Min Act: -0.0000

Data Index: 1626586 (Python Code)

Max Activating Token Index: 537

Text #19

Max Range: 4.3791. Min Range: -4.3791

Max Act: 2.7126. Min Act: -0.0001

Data Index: 1407000 (Python Code)

Max Activating Token Index: 79