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

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

Neuron 3664 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9311. Min Range: -0.9311

Max Act: 0.8883. Min Act: -0.0000

Data Index: 760533 (C4 (Web Text))

Max Activating Token Index: 428

Text #1

Max Range: 0.9311. Min Range: -0.9311

Max Act: 0.9240. Min Act: -0.0000

Data Index: 687294 (C4 (Web Text))

Max Activating Token Index: 960

Text #2

Max Range: 0.9311. Min Range: -0.9311

Max Act: 0.9191. Min Act: -0.0000

Data Index: 166923 (C4 (Web Text))

Max Activating Token Index: 947

Text #3

Max Range: 0.9311. Min Range: -0.9311

Max Act: 0.8588. Min Act: -0.0000

Data Index: 1426884 (Python Code)

Max Activating Token Index: 956

Text #4

Max Range: 0.9311. Min Range: -0.9311

Max Act: 0.9311. Min Act: -0.0000

Data Index: 1261999 (C4 (Web Text))

Max Activating Token Index: 434

Text #5

Max Range: 0.9311. Min Range: -0.9311

Max Act: 0.8899. Min Act: -0.0000

Data Index: 616847 (C4 (Web Text))

Max Activating Token Index: 482

Text #6

Max Range: 0.9311. Min Range: -0.9311

Max Act: 0.8477. Min Act: -0.0000

Data Index: 1482618 (Python Code)

Max Activating Token Index: 869

Text #7

Max Range: 0.9311. Min Range: -0.9311

Max Act: 0.8496. Min Act: -0.0000

Data Index: 1607445 (Python Code)

Max Activating Token Index: 460

Text #8

Max Range: 0.9311. Min Range: -0.9311

Max Act: 0.7826. Min Act: -0.0000

Data Index: 960411 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 0.9311. Min Range: -0.9311

Max Act: 0.8251. Min Act: -0.0000

Data Index: 945272 (C4 (Web Text))

Max Activating Token Index: 940

Text #10

Max Range: 0.9311. Min Range: -0.9311

Max Act: 0.7772. Min Act: -0.0000

Data Index: 1468653 (Python Code)

Max Activating Token Index: 313

Text #11

Max Range: 0.9311. Min Range: -0.9311

Max Act: 0.6986. Min Act: -0.0000

Data Index: 1405007 (Python Code)

Max Activating Token Index: 154

Text #12

Max Range: 0.9311. Min Range: -0.9311

Max Act: 0.7085. Min Act: -0.0000

Data Index: 1653338 (Python Code)

Max Activating Token Index: 579

Text #13

Max Range: 0.9311. Min Range: -0.9311

Max Act: 0.6612. Min Act: -0.0000

Data Index: 866261 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 0.9311. Min Range: -0.9311

Max Act: 0.7033. Min Act: -0.0000

Data Index: 541748 (C4 (Web Text))

Max Activating Token Index: 980

Text #15

Max Range: 0.9311. Min Range: -0.9311

Max Act: 0.6723. Min Act: -0.0000

Data Index: 1362768 (Python Code)

Max Activating Token Index: 361

Text #16

Max Range: 0.9311. Min Range: -0.9311

Max Act: 0.6730. Min Act: -0.0000

Data Index: 1636382 (Python Code)

Max Activating Token Index: 567

Text #17

Max Range: 0.9311. Min Range: -0.9311

Max Act: 0.6606. Min Act: -0.0000

Data Index: 1003183 (C4 (Web Text))

Max Activating Token Index: 602

Text #18

Max Range: 0.9311. Min Range: -0.9311

Max Act: 0.6802. Min Act: -0.0000

Data Index: 1625289 (Python Code)

Max Activating Token Index: 482

Text #19

Max Range: 0.9311. Min Range: -0.9311

Max Act: 0.6777. Min Act: -0.0000

Data Index: 1555193 (Python Code)

Max Activating Token Index: 471