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

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

Neuron 1541 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: 2.6292. Min Range: -2.6292

Max Act: 2.5144. Min Act: -0.0000

Data Index: 657671 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 2.6292. Min Range: -2.6292

Max Act: 2.6292. Min Act: -0.0000

Data Index: 981319 (C4 (Web Text))

Max Activating Token Index: 595

Text #2

Max Range: 2.6292. Min Range: -2.6292

Max Act: 2.3968. Min Act: -0.0000

Data Index: 342445 (C4 (Web Text))

Max Activating Token Index: 799

Text #3

Max Range: 2.6292. Min Range: -2.6292

Max Act: 2.5022. Min Act: -0.0000

Data Index: 1266378 (C4 (Web Text))

Max Activating Token Index: 526

Text #4

Max Range: 2.6292. Min Range: -2.6292

Max Act: 2.5860. Min Act: -0.0000

Data Index: 1000912 (C4 (Web Text))

Max Activating Token Index: 997

Text #5

Max Range: 2.6292. Min Range: -2.6292

Max Act: 2.2998. Min Act: -0.0000

Data Index: 518741 (C4 (Web Text))

Max Activating Token Index: 426

Text #6

Max Range: 2.6292. Min Range: -2.6292

Max Act: 2.2890. Min Act: -0.0000

Data Index: 747718 (C4 (Web Text))

Max Activating Token Index: 540

Text #7

Max Range: 2.6292. Min Range: -2.6292

Max Act: 2.3986. Min Act: -0.0000

Data Index: 297589 (C4 (Web Text))

Max Activating Token Index: 157

Text #8

Max Range: 2.6292. Min Range: -2.6292

Max Act: 2.4030. Min Act: -0.0000

Data Index: 559862 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 2.6292. Min Range: -2.6292

Max Act: 2.3912. Min Act: -0.0000

Data Index: 255296 (C4 (Web Text))

Max Activating Token Index: 702

Text #10

Max Range: 2.6292. Min Range: -2.6292

Max Act: 2.3759. Min Act: -0.0000

Data Index: 216846 (C4 (Web Text))

Max Activating Token Index: 979

Text #11

Max Range: 2.6292. Min Range: -2.6292

Max Act: 2.2478. Min Act: -0.0000

Data Index: 1297817 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 2.6292. Min Range: -2.6292

Max Act: 2.3560. Min Act: -0.0000

Data Index: 349708 (C4 (Web Text))

Max Activating Token Index: 866

Text #13

Max Range: 2.6292. Min Range: -2.6292

Max Act: 2.3332. Min Act: -0.0000

Data Index: 756173 (C4 (Web Text))

Max Activating Token Index: 934

Text #14

Max Range: 2.6292. Min Range: -2.6292

Max Act: 2.1172. Min Act: -0.0000

Data Index: 864535 (C4 (Web Text))

Max Activating Token Index: 356

Text #15

Max Range: 2.6292. Min Range: -2.6292

Max Act: 2.2079. Min Act: -0.0000

Data Index: 50672 (C4 (Web Text))

Max Activating Token Index: 952

Text #16

Max Range: 2.6292. Min Range: -2.6292

Max Act: 2.0888. Min Act: -0.0000

Data Index: 670300 (C4 (Web Text))

Max Activating Token Index: 738

Text #17

Max Range: 2.6292. Min Range: -2.6292

Max Act: 2.1813. Min Act: -0.0000

Data Index: 452508 (C4 (Web Text))

Max Activating Token Index: 722

Text #18

Max Range: 2.6292. Min Range: -2.6292

Max Act: 2.1870. Min Act: -0.0000

Data Index: 1239761 (C4 (Web Text))

Max Activating Token Index: 399

Text #19

Max Range: 2.6292. Min Range: -2.6292

Max Act: 2.1637. Min Act: -0.0000

Data Index: 782596 (C4 (Web Text))

Max Activating Token Index: 912