Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3405 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2226. Min Range: -0.2226

Max Act: 0.2226. Min Act: -0.0001

Data Index: 1578697 (Python Code)

Max Activating Token Index: 966

Text #1

Max Range: 0.2226. Min Range: -0.2226

Max Act: 0.1848. Min Act: -0.0001

Data Index: 1426740 (Python Code)

Max Activating Token Index: 915

Text #2

Max Range: 0.2226. Min Range: -0.2226

Max Act: 0.1911. Min Act: -0.0001

Data Index: 1557724 (Python Code)

Max Activating Token Index: 91

Text #3

Max Range: 0.2226. Min Range: -0.2226

Max Act: 0.1668. Min Act: -0.0001

Data Index: 1390251 (Python Code)

Max Activating Token Index: 496

Text #4

Max Range: 0.2226. Min Range: -0.2226

Max Act: 0.1792. Min Act: -0.0001

Data Index: 960621 (C4 (Web Text))

Max Activating Token Index: 11

Text #5

Max Range: 0.2226. Min Range: -0.2226

Max Act: 0.1828. Min Act: -0.0001

Data Index: 1637691 (Python Code)

Max Activating Token Index: 293

Text #6

Max Range: 0.2226. Min Range: -0.2226

Max Act: 0.1758. Min Act: -0.0000

Data Index: 1230124 (C4 (Web Text))

Max Activating Token Index: 282

Text #7

Max Range: 0.2226. Min Range: -0.2226

Max Act: 0.1673. Min Act: -0.0000

Data Index: 497388 (C4 (Web Text))

Max Activating Token Index: 148

Text #8

Max Range: 0.2226. Min Range: -0.2226

Max Act: 0.1677. Min Act: -0.0000

Data Index: 583209 (C4 (Web Text))

Max Activating Token Index: 309

Text #9

Max Range: 0.2226. Min Range: -0.2226

Max Act: 0.1655. Min Act: -0.0000

Data Index: 106405 (C4 (Web Text))

Max Activating Token Index: 807

Text #10

Max Range: 0.2226. Min Range: -0.2226

Max Act: 0.1574. Min Act: -0.0000

Data Index: 1070466 (C4 (Web Text))

Max Activating Token Index: 281

Text #11

Max Range: 0.2226. Min Range: -0.2226

Max Act: 0.1654. Min Act: -0.0001

Data Index: 1367796 (Python Code)

Max Activating Token Index: 240

Text #12

Max Range: 0.2226. Min Range: -0.2226

Max Act: 0.1531. Min Act: -0.0001

Data Index: 587121 (C4 (Web Text))

Max Activating Token Index: 825

Text #13

Max Range: 0.2226. Min Range: -0.2226

Max Act: 0.1524. Min Act: -0.0000

Data Index: 991628 (C4 (Web Text))

Max Activating Token Index: 770

Text #14

Max Range: 0.2226. Min Range: -0.2226

Max Act: 0.1469. Min Act: -0.0001

Data Index: 1463527 (Python Code)

Max Activating Token Index: 149

Text #15

Max Range: 0.2226. Min Range: -0.2226

Max Act: 0.1617. Min Act: -0.0000

Data Index: 264592 (C4 (Web Text))

Max Activating Token Index: 601

Text #16

Max Range: 0.2226. Min Range: -0.2226

Max Act: 0.1531. Min Act: -0.0001

Data Index: 238424 (C4 (Web Text))

Max Activating Token Index: 621

Text #17

Max Range: 0.2226. Min Range: -0.2226

Max Act: 0.1577. Min Act: -0.0000

Data Index: 24924 (C4 (Web Text))

Max Activating Token Index: 702

Text #18

Max Range: 0.2226. Min Range: -0.2226

Max Act: 0.1533. Min Act: -0.0000

Data Index: 260089 (C4 (Web Text))

Max Activating Token Index: 255

Text #19

Max Range: 0.2226. Min Range: -0.2226

Max Act: 0.1520. Min Act: -0.0001

Data Index: 1015505 (C4 (Web Text))

Max Activating Token Index: 168