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

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

Neuron 3479 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: 2.9542. Min Range: -2.9542

Max Act: 2.9542. Min Act: -0.0000

Data Index: 1605050 (Python Code)

Max Activating Token Index: 46

Text #1

Max Range: 2.9542. Min Range: -2.9542

Max Act: 2.1697. Min Act: -0.0000

Data Index: 1649030 (Python Code)

Max Activating Token Index: 291

Text #2

Max Range: 2.9542. Min Range: -2.9542

Max Act: 2.1115. Min Act: -0.0000

Data Index: 1502452 (Python Code)

Max Activating Token Index: 363

Text #3

Max Range: 2.9542. Min Range: -2.9542

Max Act: 2.1539. Min Act: -0.0000

Data Index: 1474223 (Python Code)

Max Activating Token Index: 795

Text #4

Max Range: 2.9542. Min Range: -2.9542

Max Act: 1.8680. Min Act: -0.0000

Data Index: 1567159 (Python Code)

Max Activating Token Index: 431

Text #5

Max Range: 2.9542. Min Range: -2.9542

Max Act: 1.8397. Min Act: -0.0000

Data Index: 1641045 (Python Code)

Max Activating Token Index: 319

Text #6

Max Range: 2.9542. Min Range: -2.9542

Max Act: 1.6693. Min Act: -0.0000

Data Index: 1368964 (Python Code)

Max Activating Token Index: 177

Text #7

Max Range: 2.9542. Min Range: -2.9542

Max Act: 1.6155. Min Act: -0.0000

Data Index: 503451 (C4 (Web Text))

Max Activating Token Index: 46

Text #8

Max Range: 2.9542. Min Range: -2.9542

Max Act: 1.7050. Min Act: -0.0000

Data Index: 1638984 (Python Code)

Max Activating Token Index: 865

Text #9

Max Range: 2.9542. Min Range: -2.9542

Max Act: 1.5612. Min Act: -0.0000

Data Index: 1074053 (C4 (Web Text))

Max Activating Token Index: 903

Text #10

Max Range: 2.9542. Min Range: -2.9542

Max Act: 1.5624. Min Act: -0.0000

Data Index: 1298553 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 2.9542. Min Range: -2.9542

Max Act: 1.4612. Min Act: -0.0000

Data Index: 1625395 (Python Code)

Max Activating Token Index: 230

Text #12

Max Range: 2.9542. Min Range: -2.9542

Max Act: 1.6024. Min Act: -0.0000

Data Index: 1617290 (Python Code)

Max Activating Token Index: 258

Text #13

Max Range: 2.9542. Min Range: -2.9542

Max Act: 1.4430. Min Act: -0.0000

Data Index: 808820 (C4 (Web Text))

Max Activating Token Index: 764

Text #14

Max Range: 2.9542. Min Range: -2.9542

Max Act: 1.5075. Min Act: -0.0000

Data Index: 1288141 (C4 (Web Text))

Max Activating Token Index: 373

Text #15

Max Range: 2.9542. Min Range: -2.9542

Max Act: 1.3988. Min Act: -0.0000

Data Index: 1466513 (Python Code)

Max Activating Token Index: 620

Text #16

Max Range: 2.9542. Min Range: -2.9542

Max Act: 1.3977. Min Act: -0.0000

Data Index: 494334 (C4 (Web Text))

Max Activating Token Index: 226

Text #17

Max Range: 2.9542. Min Range: -2.9542

Max Act: 1.3974. Min Act: -0.0000

Data Index: 584964 (C4 (Web Text))

Max Activating Token Index: 600

Text #18

Max Range: 2.9542. Min Range: -2.9542

Max Act: 1.3723. Min Act: -0.0000

Data Index: 1567280 (Python Code)

Max Activating Token Index: 281

Text #19

Max Range: 2.9542. Min Range: -2.9542

Max Act: 1.2843. Min Act: -0.0000

Data Index: 1458245 (Python Code)

Max Activating Token Index: 357