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

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

Neuron 408 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7164. Min Range: -4.7164

Max Act: 4.7164. Min Act: -0.0000

Data Index: 328395 (C4 (Web Text))

Max Activating Token Index: 762

Text #1

Max Range: 4.7164. Min Range: -4.7164

Max Act: 4.2047. Min Act: -0.0001

Data Index: 694113 (C4 (Web Text))

Max Activating Token Index: 666

Text #2

Max Range: 4.7164. Min Range: -4.7164

Max Act: 3.1491. Min Act: -0.0000

Data Index: 240084 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 4.7164. Min Range: -4.7164

Max Act: 3.1374. Min Act: -0.0000

Data Index: 556516 (C4 (Web Text))

Max Activating Token Index: 25

Text #4

Max Range: 4.7164. Min Range: -4.7164

Max Act: 3.1752. Min Act: -0.0000

Data Index: 322010 (C4 (Web Text))

Max Activating Token Index: 945

Text #5

Max Range: 4.7164. Min Range: -4.7164

Max Act: 3.4042. Min Act: -0.0001

Data Index: 698863 (C4 (Web Text))

Max Activating Token Index: 152

Text #6

Max Range: 4.7164. Min Range: -4.7164

Max Act: 3.1472. Min Act: -0.0000

Data Index: 231455 (C4 (Web Text))

Max Activating Token Index: 104

Text #7

Max Range: 4.7164. Min Range: -4.7164

Max Act: 3.1150. Min Act: -0.0000

Data Index: 382332 (C4 (Web Text))

Max Activating Token Index: 938

Text #8

Max Range: 4.7164. Min Range: -4.7164

Max Act: 3.0885. Min Act: -0.0000

Data Index: 632130 (C4 (Web Text))

Max Activating Token Index: 279

Text #9

Max Range: 4.7164. Min Range: -4.7164

Max Act: 2.8747. Min Act: -0.0000

Data Index: 784960 (C4 (Web Text))

Max Activating Token Index: 174

Text #10

Max Range: 4.7164. Min Range: -4.7164

Max Act: 2.8468. Min Act: -0.0000

Data Index: 115191 (C4 (Web Text))

Max Activating Token Index: 377

Text #11

Max Range: 4.7164. Min Range: -4.7164

Max Act: 2.9809. Min Act: -0.0000

Data Index: 702273 (C4 (Web Text))

Max Activating Token Index: 325

Text #12

Max Range: 4.7164. Min Range: -4.7164

Max Act: 3.0657. Min Act: -0.0000

Data Index: 35608 (C4 (Web Text))

Max Activating Token Index: 816

Text #13

Max Range: 4.7164. Min Range: -4.7164

Max Act: 2.9526. Min Act: -0.0000

Data Index: 771166 (C4 (Web Text))

Max Activating Token Index: 753

Text #14

Max Range: 4.7164. Min Range: -4.7164

Max Act: 3.0409. Min Act: -0.0001

Data Index: 663902 (C4 (Web Text))

Max Activating Token Index: 950

Text #15

Max Range: 4.7164. Min Range: -4.7164

Max Act: 2.5666. Min Act: -0.0000

Data Index: 476556 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 4.7164. Min Range: -4.7164

Max Act: 2.8361. Min Act: -0.0000

Data Index: 201372 (C4 (Web Text))

Max Activating Token Index: 606

Text #17

Max Range: 4.7164. Min Range: -4.7164

Max Act: 2.7010. Min Act: -0.0000

Data Index: 187470 (C4 (Web Text))

Max Activating Token Index: 620

Text #18

Max Range: 4.7164. Min Range: -4.7164

Max Act: 2.8318. Min Act: -0.0000

Data Index: 350429 (C4 (Web Text))

Max Activating Token Index: 945

Text #19

Max Range: 4.7164. Min Range: -4.7164

Max Act: 3.1475. Min Act: -0.0000

Data Index: 322351 (C4 (Web Text))

Max Activating Token Index: 779