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

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

Neuron 864 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.3301. Min Act: -0.0001

Data Index: 1049023 (C4 (Web Text))

Max Activating Token Index: 182

Text #1

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.3112. Min Act: -0.0001

Data Index: 233954 (C4 (Web Text))

Max Activating Token Index: 530

Text #2

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.2352. Min Act: -0.0001

Data Index: 997205 (C4 (Web Text))

Max Activating Token Index: 527

Text #3

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.2029. Min Act: -0.0001

Data Index: 783851 (C4 (Web Text))

Max Activating Token Index: 299

Text #4

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.2118. Min Act: -0.0001

Data Index: 808627 (C4 (Web Text))

Max Activating Token Index: 392

Text #5

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.1951. Min Act: -0.0001

Data Index: 1003491 (C4 (Web Text))

Max Activating Token Index: 149

Text #6

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.1976. Min Act: -0.0001

Data Index: 133875 (C4 (Web Text))

Max Activating Token Index: 429

Text #7

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.2062. Min Act: -0.0001

Data Index: 433147 (C4 (Web Text))

Max Activating Token Index: 244

Text #8

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.1833. Min Act: -0.0001

Data Index: 583357 (C4 (Web Text))

Max Activating Token Index: 571

Text #9

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.1834. Min Act: -0.0001

Data Index: 90241 (C4 (Web Text))

Max Activating Token Index: 337

Text #10

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.1635. Min Act: -0.0001

Data Index: 383745 (C4 (Web Text))

Max Activating Token Index: 152

Text #11

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.1728. Min Act: -0.0001

Data Index: 723668 (C4 (Web Text))

Max Activating Token Index: 699

Text #12

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.1909. Min Act: -0.0001

Data Index: 388848 (C4 (Web Text))

Max Activating Token Index: 168

Text #13

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.1644. Min Act: -0.0001

Data Index: 1126115 (C4 (Web Text))

Max Activating Token Index: 686

Text #14

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.1694. Min Act: -0.0001

Data Index: 1170478 (C4 (Web Text))

Max Activating Token Index: 374

Text #15

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.1507. Min Act: -0.0001

Data Index: 1637019 (Python Code)

Max Activating Token Index: 235

Text #16

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.1616. Min Act: -0.0001

Data Index: 34834 (C4 (Web Text))

Max Activating Token Index: 61

Text #17

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.1648. Min Act: -0.0001

Data Index: 1003252 (C4 (Web Text))

Max Activating Token Index: 186

Text #18

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.1598. Min Act: -0.0001

Data Index: 1333210 (C4 (Web Text))

Max Activating Token Index: 539

Text #19

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.1536. Min Act: -0.0001

Data Index: 862146 (C4 (Web Text))

Max Activating Token Index: 393