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

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

Neuron 1653 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2433. Min Range: -1.2433

Max Act: 1.2203. Min Act: -0.0000

Data Index: 343558 (C4 (Web Text))

Max Activating Token Index: 181

Text #1

Max Range: 1.2433. Min Range: -1.2433

Max Act: 1.2433. Min Act: -0.0000

Data Index: 1087757 (C4 (Web Text))

Max Activating Token Index: 806

Text #2

Max Range: 1.2433. Min Range: -1.2433

Max Act: 1.0985. Min Act: -0.0000

Data Index: 648929 (C4 (Web Text))

Max Activating Token Index: 678

Text #3

Max Range: 1.2433. Min Range: -1.2433

Max Act: 1.0768. Min Act: -0.0000

Data Index: 1005404 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 1.2433. Min Range: -1.2433

Max Act: 1.0826. Min Act: -0.0000

Data Index: 892846 (C4 (Web Text))

Max Activating Token Index: 457

Text #5

Max Range: 1.2433. Min Range: -1.2433

Max Act: 0.9595. Min Act: -0.0000

Data Index: 1460254 (Python Code)

Max Activating Token Index: 232

Text #6

Max Range: 1.2433. Min Range: -1.2433

Max Act: 1.0100. Min Act: -0.0000

Data Index: 624383 (C4 (Web Text))

Max Activating Token Index: 79

Text #7

Max Range: 1.2433. Min Range: -1.2433

Max Act: 1.0102. Min Act: -0.0000

Data Index: 1455874 (Python Code)

Max Activating Token Index: 184

Text #8

Max Range: 1.2433. Min Range: -1.2433

Max Act: 0.9504. Min Act: -0.0000

Data Index: 802423 (C4 (Web Text))

Max Activating Token Index: 742

Text #9

Max Range: 1.2433. Min Range: -1.2433

Max Act: 0.9227. Min Act: -0.0000

Data Index: 1137142 (C4 (Web Text))

Max Activating Token Index: 734

Text #10

Max Range: 1.2433. Min Range: -1.2433

Max Act: 0.9926. Min Act: -0.0000

Data Index: 1414589 (Python Code)

Max Activating Token Index: 139

Text #11

Max Range: 1.2433. Min Range: -1.2433

Max Act: 0.9931. Min Act: -0.0000

Data Index: 30651 (C4 (Web Text))

Max Activating Token Index: 63

Text #12

Max Range: 1.2433. Min Range: -1.2433

Max Act: 0.9897. Min Act: -0.0000

Data Index: 519296 (C4 (Web Text))

Max Activating Token Index: 299

Text #13

Max Range: 1.2433. Min Range: -1.2433

Max Act: 0.9250. Min Act: -0.0000

Data Index: 1172024 (C4 (Web Text))

Max Activating Token Index: 74

Text #14

Max Range: 1.2433. Min Range: -1.2433

Max Act: 0.9809. Min Act: -0.0000

Data Index: 479667 (C4 (Web Text))

Max Activating Token Index: 68

Text #15

Max Range: 1.2433. Min Range: -1.2433

Max Act: 0.9965. Min Act: -0.0000

Data Index: 247842 (C4 (Web Text))

Max Activating Token Index: 432

Text #16

Max Range: 1.2433. Min Range: -1.2433

Max Act: 0.8618. Min Act: -0.0000

Data Index: 974304 (C4 (Web Text))

Max Activating Token Index: 465

Text #17

Max Range: 1.2433. Min Range: -1.2433

Max Act: 0.8810. Min Act: -0.0000

Data Index: 957379 (C4 (Web Text))

Max Activating Token Index: 425

Text #18

Max Range: 1.2433. Min Range: -1.2433

Max Act: 0.9895. Min Act: -0.0000

Data Index: 1619135 (Python Code)

Max Activating Token Index: 163

Text #19

Max Range: 1.2433. Min Range: -1.2433

Max Act: 0.8797. Min Act: -0.0000

Data Index: 932236 (C4 (Web Text))

Max Activating Token Index: 704