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

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

Neuron 146 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: 4.7995. Min Range: -4.7995

Max Act: 4.7995. Min Act: -0.0000

Data Index: 192473 (C4 (Web Text))

Max Activating Token Index: 532

Text #1

Max Range: 4.7995. Min Range: -4.7995

Max Act: 4.1247. Min Act: -0.0000

Data Index: 292096 (C4 (Web Text))

Max Activating Token Index: 98

Text #2

Max Range: 4.7995. Min Range: -4.7995

Max Act: 4.2654. Min Act: -0.0000

Data Index: 664002 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 4.7995. Min Range: -4.7995

Max Act: 3.9674. Min Act: -0.0000

Data Index: 202692 (C4 (Web Text))

Max Activating Token Index: 278

Text #4

Max Range: 4.7995. Min Range: -4.7995

Max Act: 4.0879. Min Act: -0.0000

Data Index: 621846 (C4 (Web Text))

Max Activating Token Index: 182

Text #5

Max Range: 4.7995. Min Range: -4.7995

Max Act: 3.8800. Min Act: -0.0000

Data Index: 466565 (C4 (Web Text))

Max Activating Token Index: 354

Text #6

Max Range: 4.7995. Min Range: -4.7995

Max Act: 3.8564. Min Act: -0.0000

Data Index: 805058 (C4 (Web Text))

Max Activating Token Index: 860

Text #7

Max Range: 4.7995. Min Range: -4.7995

Max Act: 3.8004. Min Act: -0.0000

Data Index: 1338328 (C4 (Web Text))

Max Activating Token Index: 449

Text #8

Max Range: 4.7995. Min Range: -4.7995

Max Act: 3.7876. Min Act: -0.0000

Data Index: 511664 (C4 (Web Text))

Max Activating Token Index: 743

Text #9

Max Range: 4.7995. Min Range: -4.7995

Max Act: 3.9271. Min Act: -0.0000

Data Index: 260890 (C4 (Web Text))

Max Activating Token Index: 799

Text #10

Max Range: 4.7995. Min Range: -4.7995

Max Act: 3.8816. Min Act: -0.0000

Data Index: 346294 (C4 (Web Text))

Max Activating Token Index: 341

Text #11

Max Range: 4.7995. Min Range: -4.7995

Max Act: 3.8709. Min Act: -0.0000

Data Index: 882051 (C4 (Web Text))

Max Activating Token Index: 589

Text #12

Max Range: 4.7995. Min Range: -4.7995

Max Act: 3.3026. Min Act: -0.0000

Data Index: 5392 (C4 (Web Text))

Max Activating Token Index: 361

Text #13

Max Range: 4.7995. Min Range: -4.7995

Max Act: 4.1160. Min Act: -0.0000

Data Index: 599240 (C4 (Web Text))

Max Activating Token Index: 243

Text #14

Max Range: 4.7995. Min Range: -4.7995

Max Act: 3.7870. Min Act: -0.0000

Data Index: 827735 (C4 (Web Text))

Max Activating Token Index: 514

Text #15

Max Range: 4.7995. Min Range: -4.7995

Max Act: 3.6071. Min Act: -0.0000

Data Index: 972738 (C4 (Web Text))

Max Activating Token Index: 962

Text #16

Max Range: 4.7995. Min Range: -4.7995

Max Act: 3.4531. Min Act: -0.0000

Data Index: 209264 (C4 (Web Text))

Max Activating Token Index: 479

Text #17

Max Range: 4.7995. Min Range: -4.7995

Max Act: 3.2881. Min Act: -0.0000

Data Index: 1326076 (C4 (Web Text))

Max Activating Token Index: 241

Text #18

Max Range: 4.7995. Min Range: -4.7995

Max Act: 3.5958. Min Act: -0.0000

Data Index: 144283 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 4.7995. Min Range: -4.7995

Max Act: 3.4282. Min Act: -0.0000

Data Index: 777859 (C4 (Web Text))

Max Activating Token Index: 576