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

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

Neuron 1426 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: 1.3455. Min Range: -1.3455

Max Act: 1.2962. Min Act: -0.0000

Data Index: 844331 (C4 (Web Text))

Max Activating Token Index: 889

Text #1

Max Range: 1.3455. Min Range: -1.3455

Max Act: 1.3455. Min Act: -0.0000

Data Index: 152949 (C4 (Web Text))

Max Activating Token Index: 686

Text #2

Max Range: 1.3455. Min Range: -1.3455

Max Act: 1.2301. Min Act: -0.0000

Data Index: 1144620 (C4 (Web Text))

Max Activating Token Index: 976

Text #3

Max Range: 1.3455. Min Range: -1.3455

Max Act: 1.2248. Min Act: -0.0000

Data Index: 407231 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 1.3455. Min Range: -1.3455

Max Act: 1.1669. Min Act: -0.0000

Data Index: 1547132 (Python Code)

Max Activating Token Index: 190

Text #5

Max Range: 1.3455. Min Range: -1.3455

Max Act: 1.2647. Min Act: -0.0000

Data Index: 877812 (C4 (Web Text))

Max Activating Token Index: 534

Text #6

Max Range: 1.3455. Min Range: -1.3455

Max Act: 1.1733. Min Act: -0.0000

Data Index: 717633 (C4 (Web Text))

Max Activating Token Index: 825

Text #7

Max Range: 1.3455. Min Range: -1.3455

Max Act: 1.0760. Min Act: -0.0000

Data Index: 419721 (C4 (Web Text))

Max Activating Token Index: 603

Text #8

Max Range: 1.3455. Min Range: -1.3455

Max Act: 1.1188. Min Act: -0.0000

Data Index: 255001 (C4 (Web Text))

Max Activating Token Index: 713

Text #9

Max Range: 1.3455. Min Range: -1.3455

Max Act: 1.1427. Min Act: -0.0000

Data Index: 133789 (C4 (Web Text))

Max Activating Token Index: 334

Text #10

Max Range: 1.3455. Min Range: -1.3455

Max Act: 1.1057. Min Act: -0.0000

Data Index: 1007284 (C4 (Web Text))

Max Activating Token Index: 385

Text #11

Max Range: 1.3455. Min Range: -1.3455

Max Act: 1.1132. Min Act: -0.0000

Data Index: 1518522 (Python Code)

Max Activating Token Index: 521

Text #12

Max Range: 1.3455. Min Range: -1.3455

Max Act: 1.0475. Min Act: -0.0000

Data Index: 640821 (C4 (Web Text))

Max Activating Token Index: 708

Text #13

Max Range: 1.3455. Min Range: -1.3455

Max Act: 1.0863. Min Act: -0.0000

Data Index: 1388101 (Python Code)

Max Activating Token Index: 1016

Text #14

Max Range: 1.3455. Min Range: -1.3455

Max Act: 0.9917. Min Act: -0.0000

Data Index: 1541167 (Python Code)

Max Activating Token Index: 189

Text #15

Max Range: 1.3455. Min Range: -1.3455

Max Act: 1.0568. Min Act: -0.0000

Data Index: 4748 (C4 (Web Text))

Max Activating Token Index: 681

Text #16

Max Range: 1.3455. Min Range: -1.3455

Max Act: 1.0100. Min Act: -0.0000

Data Index: 1322664 (C4 (Web Text))

Max Activating Token Index: 116

Text #17

Max Range: 1.3455. Min Range: -1.3455

Max Act: 1.0406. Min Act: -0.0000

Data Index: 718223 (C4 (Web Text))

Max Activating Token Index: 123

Text #18

Max Range: 1.3455. Min Range: -1.3455

Max Act: 0.9659. Min Act: -0.0000

Data Index: 1644895 (Python Code)

Max Activating Token Index: 655

Text #19

Max Range: 1.3455. Min Range: -1.3455

Max Act: 1.0245. Min Act: -0.0000

Data Index: 1479009 (Python Code)

Max Activating Token Index: 103