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

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

Neuron 2316 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: 0.2649. Min Range: -0.2649

Max Act: 0.2536. Min Act: -0.0000

Data Index: 316058 (C4 (Web Text))

Max Activating Token Index: 758

Text #1

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2649. Min Act: -0.0000

Data Index: 639688 (C4 (Web Text))

Max Activating Token Index: 382

Text #2

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2299. Min Act: -0.0000

Data Index: 1063857 (C4 (Web Text))

Max Activating Token Index: 929

Text #3

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2213. Min Act: -0.0000

Data Index: 919 (C4 (Web Text))

Max Activating Token Index: 522

Text #4

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2042. Min Act: -0.0000

Data Index: 31603 (C4 (Web Text))

Max Activating Token Index: 872

Text #5

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2076. Min Act: -0.0000

Data Index: 1426121 (Python Code)

Max Activating Token Index: 117

Text #6

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.1994. Min Act: -0.0000

Data Index: 431212 (C4 (Web Text))

Max Activating Token Index: 371

Text #7

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.1994. Min Act: -0.0000

Data Index: 417735 (C4 (Web Text))

Max Activating Token Index: 478

Text #8

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.1850. Min Act: -0.0000

Data Index: 659803 (C4 (Web Text))

Max Activating Token Index: 305

Text #9

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.1832. Min Act: -0.0000

Data Index: 985998 (C4 (Web Text))

Max Activating Token Index: 791

Text #10

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.1800. Min Act: -0.0000

Data Index: 556382 (C4 (Web Text))

Max Activating Token Index: 506

Text #11

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.1662. Min Act: -0.0000

Data Index: 550782 (C4 (Web Text))

Max Activating Token Index: 806

Text #12

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.1838. Min Act: -0.0000

Data Index: 410036 (C4 (Web Text))

Max Activating Token Index: 802

Text #13

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.1839. Min Act: -0.0000

Data Index: 1379022 (Python Code)

Max Activating Token Index: 655

Text #14

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.1697. Min Act: -0.0000

Data Index: 795329 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.1647. Min Act: -0.0000

Data Index: 1309287 (C4 (Web Text))

Max Activating Token Index: 231

Text #16

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.1687. Min Act: -0.0000

Data Index: 280194 (C4 (Web Text))

Max Activating Token Index: 559

Text #17

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.1661. Min Act: -0.0000

Data Index: 1630766 (Python Code)

Max Activating Token Index: 914

Text #18

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.1534. Min Act: -0.0000

Data Index: 1600425 (Python Code)

Max Activating Token Index: 971

Text #19

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.1675. Min Act: -0.0000

Data Index: 146250 (C4 (Web Text))

Max Activating Token Index: 312