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

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

Neuron 2605 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.2069. Min Act: -0.0002

Data Index: 896411 (C4 (Web Text))

Max Activating Token Index: 824

Text #1

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1810. Min Act: -0.0002

Data Index: 1299604 (C4 (Web Text))

Max Activating Token Index: 890

Text #2

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1780. Min Act: -0.0002

Data Index: 313065 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1786. Min Act: -0.0002

Data Index: 985255 (C4 (Web Text))

Max Activating Token Index: 141

Text #4

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1783. Min Act: -0.0002

Data Index: 1013506 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1764. Min Act: -0.0002

Data Index: 1147204 (C4 (Web Text))

Max Activating Token Index: 120

Text #6

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1739. Min Act: -0.0002

Data Index: 1316741 (C4 (Web Text))

Max Activating Token Index: 7

Text #7

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1846. Min Act: -0.0002

Data Index: 380766 (C4 (Web Text))

Max Activating Token Index: 216

Text #8

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1599. Min Act: -0.0002

Data Index: 440969 (C4 (Web Text))

Max Activating Token Index: 302

Text #9

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1773. Min Act: -0.0002

Data Index: 1108774 (C4 (Web Text))

Max Activating Token Index: 148

Text #10

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1767. Min Act: -0.0002

Data Index: 40960 (C4 (Web Text))

Max Activating Token Index: 66

Text #11

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1893. Min Act: -0.0002

Data Index: 514436 (C4 (Web Text))

Max Activating Token Index: 155

Text #12

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1731. Min Act: -0.0002

Data Index: 245272 (C4 (Web Text))

Max Activating Token Index: 271

Text #13

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1745. Min Act: -0.0002

Data Index: 253317 (C4 (Web Text))

Max Activating Token Index: 441

Text #14

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1546. Min Act: -0.0002

Data Index: 398226 (C4 (Web Text))

Max Activating Token Index: 551

Text #15

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1577. Min Act: -0.0002

Data Index: 658073 (C4 (Web Text))

Max Activating Token Index: 263

Text #16

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1651. Min Act: -0.0002

Data Index: 770591 (C4 (Web Text))

Max Activating Token Index: 142

Text #17

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1640. Min Act: -0.0002

Data Index: 1233500 (C4 (Web Text))

Max Activating Token Index: 470

Text #18

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1640. Min Act: -0.0002

Data Index: 128077 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1701. Min Act: -0.0002

Data Index: 765263 (C4 (Web Text))

Max Activating Token Index: 604