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

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

Neuron 5391 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3449. Min Range: -3.3449

Max Act: 3.3449. Min Act: -0.0000

Data Index: 1370847 (Python Code)

Max Activating Token Index: 946

Text #1

Max Range: 3.3449. Min Range: -3.3449

Max Act: 2.5421. Min Act: -0.0000

Data Index: 1556282 (Python Code)

Max Activating Token Index: 312

Text #2

Max Range: 3.3449. Min Range: -3.3449

Max Act: 2.5489. Min Act: -0.0000

Data Index: 1652745 (Python Code)

Max Activating Token Index: 200

Text #3

Max Range: 3.3449. Min Range: -3.3449

Max Act: 2.2850. Min Act: -0.0000

Data Index: 1506837 (Python Code)

Max Activating Token Index: 403

Text #4

Max Range: 3.3449. Min Range: -3.3449

Max Act: 2.4673. Min Act: -0.0000

Data Index: 1634316 (Python Code)

Max Activating Token Index: 466

Text #5

Max Range: 3.3449. Min Range: -3.3449

Max Act: 2.1353. Min Act: -0.0000

Data Index: 1621140 (Python Code)

Max Activating Token Index: 395

Text #6

Max Range: 3.3449. Min Range: -3.3449

Max Act: 2.0254. Min Act: -0.0000

Data Index: 1330495 (C4 (Web Text))

Max Activating Token Index: 364

Text #7

Max Range: 3.3449. Min Range: -3.3449

Max Act: 2.1306. Min Act: -0.0000

Data Index: 1531970 (Python Code)

Max Activating Token Index: 503

Text #8

Max Range: 3.3449. Min Range: -3.3449

Max Act: 1.8062. Min Act: -0.0000

Data Index: 1233261 (C4 (Web Text))

Max Activating Token Index: 383

Text #9

Max Range: 3.3449. Min Range: -3.3449

Max Act: 1.9156. Min Act: -0.0000

Data Index: 1528178 (Python Code)

Max Activating Token Index: 205

Text #10

Max Range: 3.3449. Min Range: -3.3449

Max Act: 1.9866. Min Act: -0.0000

Data Index: 1054911 (C4 (Web Text))

Max Activating Token Index: 655

Text #11

Max Range: 3.3449. Min Range: -3.3449

Max Act: 1.8123. Min Act: -0.0000

Data Index: 590916 (C4 (Web Text))

Max Activating Token Index: 903

Text #12

Max Range: 3.3449. Min Range: -3.3449

Max Act: 1.7885. Min Act: -0.0000

Data Index: 1460504 (Python Code)

Max Activating Token Index: 440

Text #13

Max Range: 3.3449. Min Range: -3.3449

Max Act: 1.8612. Min Act: -0.0000

Data Index: 538852 (C4 (Web Text))

Max Activating Token Index: 72

Text #14

Max Range: 3.3449. Min Range: -3.3449

Max Act: 1.7253. Min Act: -0.0000

Data Index: 183397 (C4 (Web Text))

Max Activating Token Index: 545

Text #15

Max Range: 3.3449. Min Range: -3.3449

Max Act: 1.7657. Min Act: -0.0000

Data Index: 1593578 (Python Code)

Max Activating Token Index: 487

Text #16

Max Range: 3.3449. Min Range: -3.3449

Max Act: 1.7063. Min Act: -0.0000

Data Index: 681 (C4 (Web Text))

Max Activating Token Index: 309

Text #17

Max Range: 3.3449. Min Range: -3.3449

Max Act: 1.5677. Min Act: -0.0000

Data Index: 1427526 (Python Code)

Max Activating Token Index: 881

Text #18

Max Range: 3.3449. Min Range: -3.3449

Max Act: 1.5649. Min Act: -0.0000

Data Index: 600516 (C4 (Web Text))

Max Activating Token Index: 725

Text #19

Max Range: 3.3449. Min Range: -3.3449

Max Act: 1.4643. Min Act: -0.0000

Data Index: 259063 (C4 (Web Text))

Max Activating Token Index: 609