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

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

Neuron 1056 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 2.1620. Min Range: -2.1620

Max Act: 2.1620. Min Act: -0.0002

Data Index: 406572 (C4 (Web Text))

Max Activating Token Index: 446

Text #1

Max Range: 2.1620. Min Range: -2.1620

Max Act: 1.9984. Min Act: -0.0003

Data Index: 670794 (C4 (Web Text))

Max Activating Token Index: 442

Text #2

Max Range: 2.1620. Min Range: -2.1620

Max Act: 1.9113. Min Act: -0.0002

Data Index: 264205 (C4 (Web Text))

Max Activating Token Index: 383

Text #3

Max Range: 2.1620. Min Range: -2.1620

Max Act: 1.9616. Min Act: -0.0002

Data Index: 240354 (C4 (Web Text))

Max Activating Token Index: 249

Text #4

Max Range: 2.1620. Min Range: -2.1620

Max Act: 1.9404. Min Act: -0.0002

Data Index: 703722 (C4 (Web Text))

Max Activating Token Index: 447

Text #5

Max Range: 2.1620. Min Range: -2.1620

Max Act: 1.8947. Min Act: -0.0002

Data Index: 896480 (C4 (Web Text))

Max Activating Token Index: 399

Text #6

Max Range: 2.1620. Min Range: -2.1620

Max Act: 1.8500. Min Act: -0.0003

Data Index: 244301 (C4 (Web Text))

Max Activating Token Index: 554

Text #7

Max Range: 2.1620. Min Range: -2.1620

Max Act: 1.8500. Min Act: -0.0002

Data Index: 882857 (C4 (Web Text))

Max Activating Token Index: 82

Text #8

Max Range: 2.1620. Min Range: -2.1620

Max Act: 1.8575. Min Act: -0.0002

Data Index: 178863 (C4 (Web Text))

Max Activating Token Index: 924

Text #9

Max Range: 2.1620. Min Range: -2.1620

Max Act: 1.8499. Min Act: -0.0002

Data Index: 3134 (C4 (Web Text))

Max Activating Token Index: 392

Text #10

Max Range: 2.1620. Min Range: -2.1620

Max Act: 1.7704. Min Act: -0.0003

Data Index: 1029578 (C4 (Web Text))

Max Activating Token Index: 606

Text #11

Max Range: 2.1620. Min Range: -2.1620

Max Act: 1.7814. Min Act: -0.0002

Data Index: 619399 (C4 (Web Text))

Max Activating Token Index: 310

Text #12

Max Range: 2.1620. Min Range: -2.1620

Max Act: 1.7837. Min Act: -0.0002

Data Index: 116617 (C4 (Web Text))

Max Activating Token Index: 918

Text #13

Max Range: 2.1620. Min Range: -2.1620

Max Act: 1.8004. Min Act: -0.0002

Data Index: 434157 (C4 (Web Text))

Max Activating Token Index: 507

Text #14

Max Range: 2.1620. Min Range: -2.1620

Max Act: 1.7746. Min Act: -0.0002

Data Index: 109786 (C4 (Web Text))

Max Activating Token Index: 73

Text #15

Max Range: 2.1620. Min Range: -2.1620

Max Act: 1.7520. Min Act: -0.0002

Data Index: 1276385 (C4 (Web Text))

Max Activating Token Index: 801

Text #16

Max Range: 2.1620. Min Range: -2.1620

Max Act: 1.7501. Min Act: -0.0002

Data Index: 1356791 (C4 (Web Text))

Max Activating Token Index: 88

Text #17

Max Range: 2.1620. Min Range: -2.1620

Max Act: 1.7603. Min Act: -0.0002

Data Index: 1046773 (C4 (Web Text))

Max Activating Token Index: 131

Text #18

Max Range: 2.1620. Min Range: -2.1620

Max Act: 1.7379. Min Act: -0.0002

Data Index: 670948 (C4 (Web Text))

Max Activating Token Index: 932

Text #19

Max Range: 2.1620. Min Range: -2.1620

Max Act: 1.7799. Min Act: -0.0002

Data Index: 864711 (C4 (Web Text))

Max Activating Token Index: 170