Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2907 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5917. Min Range: -1.5917

Max Act: 1.5917. Min Act: -0.0000

Data Index: 1653765 (Python Code)

Max Activating Token Index: 429

Text #1

Max Range: 1.5917. Min Range: -1.5917

Max Act: 1.3777. Min Act: -0.0000

Data Index: 261721 (C4 (Web Text))

Max Activating Token Index: 307

Text #2

Max Range: 1.5917. Min Range: -1.5917

Max Act: 1.1977. Min Act: -0.0000

Data Index: 1389189 (Python Code)

Max Activating Token Index: 20

Text #3

Max Range: 1.5917. Min Range: -1.5917

Max Act: 1.0674. Min Act: -0.0000

Data Index: 640665 (C4 (Web Text))

Max Activating Token Index: 889

Text #4

Max Range: 1.5917. Min Range: -1.5917

Max Act: 1.0968. Min Act: -0.0000

Data Index: 178721 (C4 (Web Text))

Max Activating Token Index: 827

Text #5

Max Range: 1.5917. Min Range: -1.5917

Max Act: 1.1993. Min Act: -0.0000

Data Index: 486207 (C4 (Web Text))

Max Activating Token Index: 88

Text #6

Max Range: 1.5917. Min Range: -1.5917

Max Act: 1.1237. Min Act: -0.0000

Data Index: 1480636 (Python Code)

Max Activating Token Index: 493

Text #7

Max Range: 1.5917. Min Range: -1.5917

Max Act: 1.1117. Min Act: -0.0000

Data Index: 244441 (C4 (Web Text))

Max Activating Token Index: 575

Text #8

Max Range: 1.5917. Min Range: -1.5917

Max Act: 1.0804. Min Act: -0.0000

Data Index: 1255483 (C4 (Web Text))

Max Activating Token Index: 963

Text #9

Max Range: 1.5917. Min Range: -1.5917

Max Act: 0.9321. Min Act: -0.0000

Data Index: 1549910 (Python Code)

Max Activating Token Index: 726

Text #10

Max Range: 1.5917. Min Range: -1.5917

Max Act: 1.0562. Min Act: -0.0000

Data Index: 1565737 (Python Code)

Max Activating Token Index: 924

Text #11

Max Range: 1.5917. Min Range: -1.5917

Max Act: 0.9339. Min Act: -0.0000

Data Index: 1487364 (Python Code)

Max Activating Token Index: 880

Text #12

Max Range: 1.5917. Min Range: -1.5917

Max Act: 0.9935. Min Act: -0.0000

Data Index: 1371590 (Python Code)

Max Activating Token Index: 817

Text #13

Max Range: 1.5917. Min Range: -1.5917

Max Act: 1.0135. Min Act: -0.0000

Data Index: 1439625 (Python Code)

Max Activating Token Index: 826

Text #14

Max Range: 1.5917. Min Range: -1.5917

Max Act: 0.9504. Min Act: -0.0000

Data Index: 1434044 (Python Code)

Max Activating Token Index: 629

Text #15

Max Range: 1.5917. Min Range: -1.5917

Max Act: 1.0202. Min Act: -0.0000

Data Index: 787742 (C4 (Web Text))

Max Activating Token Index: 151

Text #16

Max Range: 1.5917. Min Range: -1.5917

Max Act: 0.9316. Min Act: -0.0000

Data Index: 1012015 (C4 (Web Text))

Max Activating Token Index: 726

Text #17

Max Range: 1.5917. Min Range: -1.5917

Max Act: 0.9399. Min Act: -0.0000

Data Index: 1212160 (C4 (Web Text))

Max Activating Token Index: 670

Text #18

Max Range: 1.5917. Min Range: -1.5917

Max Act: 1.0697. Min Act: -0.0000

Data Index: 466094 (C4 (Web Text))

Max Activating Token Index: 371

Text #19

Max Range: 1.5917. Min Range: -1.5917

Max Act: 0.9819. Min Act: -0.0000

Data Index: 261108 (C4 (Web Text))

Max Activating Token Index: 402