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

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

Neuron 1486 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: 3.8427. Min Range: -3.8427

Max Act: 3.8427. Min Act: -0.0000

Data Index: 327897 (C4 (Web Text))

Max Activating Token Index: 401

Text #1

Max Range: 3.8427. Min Range: -3.8427

Max Act: 3.7562. Min Act: -0.0000

Data Index: 1158155 (C4 (Web Text))

Max Activating Token Index: 1006

Text #2

Max Range: 3.8427. Min Range: -3.8427

Max Act: 3.4703. Min Act: -0.0000

Data Index: 1336690 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 3.8427. Min Range: -3.8427

Max Act: 3.6473. Min Act: -0.0000

Data Index: 1020935 (C4 (Web Text))

Max Activating Token Index: 541

Text #4

Max Range: 3.8427. Min Range: -3.8427

Max Act: 3.6053. Min Act: -0.0000

Data Index: 157615 (C4 (Web Text))

Max Activating Token Index: 574

Text #5

Max Range: 3.8427. Min Range: -3.8427

Max Act: 3.2156. Min Act: -0.0000

Data Index: 737598 (C4 (Web Text))

Max Activating Token Index: 572

Text #6

Max Range: 3.8427. Min Range: -3.8427

Max Act: 3.6811. Min Act: -0.0000

Data Index: 425916 (C4 (Web Text))

Max Activating Token Index: 353

Text #7

Max Range: 3.8427. Min Range: -3.8427

Max Act: 3.3168. Min Act: -0.0000

Data Index: 829466 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 3.8427. Min Range: -3.8427

Max Act: 3.4644. Min Act: -0.0000

Data Index: 759617 (C4 (Web Text))

Max Activating Token Index: 475

Text #9

Max Range: 3.8427. Min Range: -3.8427

Max Act: 3.4280. Min Act: -0.0000

Data Index: 1025103 (C4 (Web Text))

Max Activating Token Index: 828

Text #10

Max Range: 3.8427. Min Range: -3.8427

Max Act: 3.4283. Min Act: -0.0000

Data Index: 1305157 (C4 (Web Text))

Max Activating Token Index: 832

Text #11

Max Range: 3.8427. Min Range: -3.8427

Max Act: 3.5534. Min Act: -0.0000

Data Index: 1042132 (C4 (Web Text))

Max Activating Token Index: 125

Text #12

Max Range: 3.8427. Min Range: -3.8427

Max Act: 3.5173. Min Act: -0.0000

Data Index: 699246 (C4 (Web Text))

Max Activating Token Index: 291

Text #13

Max Range: 3.8427. Min Range: -3.8427

Max Act: 3.1940. Min Act: -0.0000

Data Index: 1237627 (C4 (Web Text))

Max Activating Token Index: 269

Text #14

Max Range: 3.8427. Min Range: -3.8427

Max Act: 3.3385. Min Act: -0.0000

Data Index: 705753 (C4 (Web Text))

Max Activating Token Index: 69

Text #15

Max Range: 3.8427. Min Range: -3.8427

Max Act: 3.1829. Min Act: -0.0000

Data Index: 370455 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 3.8427. Min Range: -3.8427

Max Act: 3.1294. Min Act: -0.0000

Data Index: 1196116 (C4 (Web Text))

Max Activating Token Index: 460

Text #17

Max Range: 3.8427. Min Range: -3.8427

Max Act: 3.2795. Min Act: -0.0000

Data Index: 48390 (C4 (Web Text))

Max Activating Token Index: 233

Text #18

Max Range: 3.8427. Min Range: -3.8427

Max Act: 3.2700. Min Act: -0.0000

Data Index: 1067010 (C4 (Web Text))

Max Activating Token Index: 963

Text #19

Max Range: 3.8427. Min Range: -3.8427

Max Act: 3.1951. Min Act: -0.0000

Data Index: 717952 (C4 (Web Text))

Max Activating Token Index: 484