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

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

Neuron 5327 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: 2.3996. Min Range: -2.3996

Max Act: 2.3996. Min Act: -0.0000

Data Index: 1500779 (Python Code)

Max Activating Token Index: 203

Text #1

Max Range: 2.3996. Min Range: -2.3996

Max Act: 2.3628. Min Act: -0.0000

Data Index: 1408147 (Python Code)

Max Activating Token Index: 653

Text #2

Max Range: 2.3996. Min Range: -2.3996

Max Act: 2.2591. Min Act: -0.0000

Data Index: 1519571 (Python Code)

Max Activating Token Index: 281

Text #3

Max Range: 2.3996. Min Range: -2.3996

Max Act: 2.2451. Min Act: 0.0000

Data Index: 1327333 (C4 (Web Text))

Max Activating Token Index: 937

Text #4

Max Range: 2.3996. Min Range: -2.3996

Max Act: 2.0889. Min Act: -0.0000

Data Index: 1370338 (Python Code)

Max Activating Token Index: 179

Text #5

Max Range: 2.3996. Min Range: -2.3996

Max Act: 2.1927. Min Act: -0.0000

Data Index: 1569712 (Python Code)

Max Activating Token Index: 154

Text #6

Max Range: 2.3996. Min Range: -2.3996

Max Act: 2.0084. Min Act: -0.0000

Data Index: 937322 (C4 (Web Text))

Max Activating Token Index: 81

Text #7

Max Range: 2.3996. Min Range: -2.3996

Max Act: 1.8133. Min Act: -0.0000

Data Index: 688165 (C4 (Web Text))

Max Activating Token Index: 702

Text #8

Max Range: 2.3996. Min Range: -2.3996

Max Act: 1.9104. Min Act: -0.0000

Data Index: 1287754 (C4 (Web Text))

Max Activating Token Index: 964

Text #9

Max Range: 2.3996. Min Range: -2.3996

Max Act: 1.9597. Min Act: -0.0000

Data Index: 1388122 (Python Code)

Max Activating Token Index: 854

Text #10

Max Range: 2.3996. Min Range: -2.3996

Max Act: 1.7194. Min Act: -0.0000

Data Index: 1469215 (Python Code)

Max Activating Token Index: 566

Text #11

Max Range: 2.3996. Min Range: -2.3996

Max Act: 1.7840. Min Act: -0.0000

Data Index: 632777 (C4 (Web Text))

Max Activating Token Index: 78

Text #12

Max Range: 2.3996. Min Range: -2.3996

Max Act: 1.7558. Min Act: -0.0000

Data Index: 1480261 (Python Code)

Max Activating Token Index: 527

Text #13

Max Range: 2.3996. Min Range: -2.3996

Max Act: 1.8369. Min Act: -0.0000

Data Index: 277608 (C4 (Web Text))

Max Activating Token Index: 908

Text #14

Max Range: 2.3996. Min Range: -2.3996

Max Act: 1.7368. Min Act: -0.0000

Data Index: 699058 (C4 (Web Text))

Max Activating Token Index: 401

Text #15

Max Range: 2.3996. Min Range: -2.3996

Max Act: 1.5947. Min Act: -0.0000

Data Index: 603246 (C4 (Web Text))

Max Activating Token Index: 17

Text #16

Max Range: 2.3996. Min Range: -2.3996

Max Act: 1.6903. Min Act: -0.0000

Data Index: 3353 (C4 (Web Text))

Max Activating Token Index: 182

Text #17

Max Range: 2.3996. Min Range: -2.3996

Max Act: 1.6825. Min Act: -0.0000

Data Index: 810391 (C4 (Web Text))

Max Activating Token Index: 886

Text #18

Max Range: 2.3996. Min Range: -2.3996

Max Act: 1.6734. Min Act: -0.0000

Data Index: 973086 (C4 (Web Text))

Max Activating Token Index: 42

Text #19

Max Range: 2.3996. Min Range: -2.3996

Max Act: 1.6576. Min Act: -0.0000

Data Index: 387917 (C4 (Web Text))

Max Activating Token Index: 183