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

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

Neuron 3492 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.9797. Min Act: -0.0000

Data Index: 1613128 (Python Code)

Max Activating Token Index: 327

Text #1

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.8236. Min Act: -0.0000

Data Index: 577632 (C4 (Web Text))

Max Activating Token Index: 981

Text #2

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.6834. Min Act: -0.0000

Data Index: 128782 (C4 (Web Text))

Max Activating Token Index: 844

Text #3

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.7680. Min Act: -0.0000

Data Index: 726091 (C4 (Web Text))

Max Activating Token Index: 807

Text #4

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.7737. Min Act: -0.0000

Data Index: 1186320 (C4 (Web Text))

Max Activating Token Index: 622

Text #5

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.7874. Min Act: -0.0000

Data Index: 241668 (C4 (Web Text))

Max Activating Token Index: 575

Text #6

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.7209. Min Act: -0.0000

Data Index: 71400 (C4 (Web Text))

Max Activating Token Index: 176

Text #7

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.6897. Min Act: -0.0000

Data Index: 1151611 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.5953. Min Act: -0.0000

Data Index: 36977 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.6785. Min Act: -0.0000

Data Index: 531558 (C4 (Web Text))

Max Activating Token Index: 138

Text #10

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.7345. Min Act: -0.0000

Data Index: 1178198 (C4 (Web Text))

Max Activating Token Index: 831

Text #11

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.7021. Min Act: -0.0000

Data Index: 1128033 (C4 (Web Text))

Max Activating Token Index: 891

Text #12

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.6171. Min Act: -0.0000

Data Index: 1483892 (Python Code)

Max Activating Token Index: 285

Text #13

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.6549. Min Act: -0.0000

Data Index: 1544034 (Python Code)

Max Activating Token Index: 370

Text #14

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.6788. Min Act: -0.0000

Data Index: 499971 (C4 (Web Text))

Max Activating Token Index: 116

Text #15

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.6863. Min Act: -0.0000

Data Index: 949398 (C4 (Web Text))

Max Activating Token Index: 136

Text #16

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.6635. Min Act: -0.0000

Data Index: 1016910 (C4 (Web Text))

Max Activating Token Index: 445

Text #17

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.7003. Min Act: -0.0000

Data Index: 22713 (C4 (Web Text))

Max Activating Token Index: 1013

Text #18

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.5768. Min Act: -0.0000

Data Index: 1002817 (C4 (Web Text))

Max Activating Token Index: 269

Text #19

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.6562. Min Act: -0.0000

Data Index: 1551904 (Python Code)

Max Activating Token Index: 253