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

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

Neuron 5588 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: 1.2959. Min Range: -1.2959

Max Act: 1.2959. Min Act: -0.0000

Data Index: 154375 (C4 (Web Text))

Max Activating Token Index: 1016

Text #1

Max Range: 1.2959. Min Range: -1.2959

Max Act: 1.0266. Min Act: -0.0000

Data Index: 916370 (C4 (Web Text))

Max Activating Token Index: 332

Text #2

Max Range: 1.2959. Min Range: -1.2959

Max Act: 1.0396. Min Act: -0.0000

Data Index: 1020087 (C4 (Web Text))

Max Activating Token Index: 274

Text #3

Max Range: 1.2959. Min Range: -1.2959

Max Act: 0.9754. Min Act: -0.0000

Data Index: 810301 (C4 (Web Text))

Max Activating Token Index: 424

Text #4

Max Range: 1.2959. Min Range: -1.2959

Max Act: 1.0242. Min Act: -0.0000

Data Index: 95791 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 1.2959. Min Range: -1.2959

Max Act: 1.0039. Min Act: -0.0000

Data Index: 825847 (C4 (Web Text))

Max Activating Token Index: 571

Text #6

Max Range: 1.2959. Min Range: -1.2959

Max Act: 1.0330. Min Act: -0.0000

Data Index: 1168586 (C4 (Web Text))

Max Activating Token Index: 966

Text #7

Max Range: 1.2959. Min Range: -1.2959

Max Act: 0.9557. Min Act: -0.0000

Data Index: 265724 (C4 (Web Text))

Max Activating Token Index: 342

Text #8

Max Range: 1.2959. Min Range: -1.2959

Max Act: 0.9244. Min Act: -0.0000

Data Index: 79010 (C4 (Web Text))

Max Activating Token Index: 194

Text #9

Max Range: 1.2959. Min Range: -1.2959

Max Act: 0.9192. Min Act: -0.0000

Data Index: 1217816 (C4 (Web Text))

Max Activating Token Index: 676

Text #10

Max Range: 1.2959. Min Range: -1.2959

Max Act: 0.9440. Min Act: -0.0000

Data Index: 166923 (C4 (Web Text))

Max Activating Token Index: 682

Text #11

Max Range: 1.2959. Min Range: -1.2959

Max Act: 0.9015. Min Act: -0.0000

Data Index: 47473 (C4 (Web Text))

Max Activating Token Index: 447

Text #12

Max Range: 1.2959. Min Range: -1.2959

Max Act: 0.8452. Min Act: -0.0000

Data Index: 988038 (C4 (Web Text))

Max Activating Token Index: 862

Text #13

Max Range: 1.2959. Min Range: -1.2959

Max Act: 0.8279. Min Act: -0.0000

Data Index: 98105 (C4 (Web Text))

Max Activating Token Index: 897

Text #14

Max Range: 1.2959. Min Range: -1.2959

Max Act: 0.8539. Min Act: -0.0000

Data Index: 1162931 (C4 (Web Text))

Max Activating Token Index: 441

Text #15

Max Range: 1.2959. Min Range: -1.2959

Max Act: 0.8618. Min Act: -0.0000

Data Index: 162052 (C4 (Web Text))

Max Activating Token Index: 683

Text #16

Max Range: 1.2959. Min Range: -1.2959

Max Act: 0.8263. Min Act: -0.0000

Data Index: 1059061 (C4 (Web Text))

Max Activating Token Index: 501

Text #17

Max Range: 1.2959. Min Range: -1.2959

Max Act: 0.8437. Min Act: -0.0000

Data Index: 185833 (C4 (Web Text))

Max Activating Token Index: 475

Text #18

Max Range: 1.2959. Min Range: -1.2959

Max Act: 0.8449. Min Act: -0.0000

Data Index: 10108 (C4 (Web Text))

Max Activating Token Index: 305

Text #19

Max Range: 1.2959. Min Range: -1.2959

Max Act: 0.7823. Min Act: -0.0000

Data Index: 1410636 (Python Code)

Max Activating Token Index: 1006