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

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

Neuron 3512 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: 5.4377. Min Range: -5.4377

Max Act: 5.4377. Min Act: -0.0000

Data Index: 1033996 (C4 (Web Text))

Max Activating Token Index: 605

Text #1

Max Range: 5.4377. Min Range: -5.4377

Max Act: 4.9613. Min Act: -0.0000

Data Index: 594756 (C4 (Web Text))

Max Activating Token Index: 715

Text #2

Max Range: 5.4377. Min Range: -5.4377

Max Act: 4.8903. Min Act: -0.0000

Data Index: 1315576 (C4 (Web Text))

Max Activating Token Index: 801

Text #3

Max Range: 5.4377. Min Range: -5.4377

Max Act: 4.7000. Min Act: -0.0000

Data Index: 846599 (C4 (Web Text))

Max Activating Token Index: 790

Text #4

Max Range: 5.4377. Min Range: -5.4377

Max Act: 4.7164. Min Act: -0.0000

Data Index: 865538 (C4 (Web Text))

Max Activating Token Index: 772

Text #5

Max Range: 5.4377. Min Range: -5.4377

Max Act: 4.1062. Min Act: -0.0000

Data Index: 698150 (C4 (Web Text))

Max Activating Token Index: 907

Text #6

Max Range: 5.4377. Min Range: -5.4377

Max Act: 4.2384. Min Act: -0.0000

Data Index: 251328 (C4 (Web Text))

Max Activating Token Index: 191

Text #7

Max Range: 5.4377. Min Range: -5.4377

Max Act: 4.2555. Min Act: -0.0000

Data Index: 105189 (C4 (Web Text))

Max Activating Token Index: 762

Text #8

Max Range: 5.4377. Min Range: -5.4377

Max Act: 4.0856. Min Act: -0.0000

Data Index: 901922 (C4 (Web Text))

Max Activating Token Index: 220

Text #9

Max Range: 5.4377. Min Range: -5.4377

Max Act: 4.0808. Min Act: -0.0000

Data Index: 546899 (C4 (Web Text))

Max Activating Token Index: 854

Text #10

Max Range: 5.4377. Min Range: -5.4377

Max Act: 4.0643. Min Act: -0.0000

Data Index: 309375 (C4 (Web Text))

Max Activating Token Index: 643

Text #11

Max Range: 5.4377. Min Range: -5.4377

Max Act: 4.0410. Min Act: -0.0000

Data Index: 644525 (C4 (Web Text))

Max Activating Token Index: 529

Text #12

Max Range: 5.4377. Min Range: -5.4377

Max Act: 4.0164. Min Act: -0.0000

Data Index: 146367 (C4 (Web Text))

Max Activating Token Index: 533

Text #13

Max Range: 5.4377. Min Range: -5.4377

Max Act: 3.9982. Min Act: -0.0000

Data Index: 1286477 (C4 (Web Text))

Max Activating Token Index: 74

Text #14

Max Range: 5.4377. Min Range: -5.4377

Max Act: 3.9960. Min Act: -0.0000

Data Index: 859757 (C4 (Web Text))

Max Activating Token Index: 433

Text #15

Max Range: 5.4377. Min Range: -5.4377

Max Act: 3.8154. Min Act: -0.0000

Data Index: 877533 (C4 (Web Text))

Max Activating Token Index: 297

Text #16

Max Range: 5.4377. Min Range: -5.4377

Max Act: 4.1237. Min Act: -0.0000

Data Index: 1169785 (C4 (Web Text))

Max Activating Token Index: 887

Text #17

Max Range: 5.4377. Min Range: -5.4377

Max Act: 3.8813. Min Act: -0.0000

Data Index: 17361 (C4 (Web Text))

Max Activating Token Index: 832

Text #18

Max Range: 5.4377. Min Range: -5.4377

Max Act: 3.8977. Min Act: -0.0000

Data Index: 1208018 (C4 (Web Text))

Max Activating Token Index: 976

Text #19

Max Range: 5.4377. Min Range: -5.4377

Max Act: 3.8950. Min Act: -0.0000

Data Index: 857865 (C4 (Web Text))

Max Activating Token Index: 344