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

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

Neuron 693 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9297. Min Range: -2.9297

Max Act: 2.6729. Min Act: -0.0000

Data Index: 190503 (C4 (Web Text))

Max Activating Token Index: 688

Text #1

Max Range: 2.9297. Min Range: -2.9297

Max Act: 2.9297. Min Act: -0.0000

Data Index: 1061368 (C4 (Web Text))

Max Activating Token Index: 694

Text #2

Max Range: 2.9297. Min Range: -2.9297

Max Act: 2.4262. Min Act: -0.0000

Data Index: 869054 (C4 (Web Text))

Max Activating Token Index: 830

Text #3

Max Range: 2.9297. Min Range: -2.9297

Max Act: 2.7295. Min Act: -0.0001

Data Index: 1468488 (Python Code)

Max Activating Token Index: 385

Text #4

Max Range: 2.9297. Min Range: -2.9297

Max Act: 2.4104. Min Act: -0.0000

Data Index: 421907 (C4 (Web Text))

Max Activating Token Index: 554

Text #5

Max Range: 2.9297. Min Range: -2.9297

Max Act: 2.4552. Min Act: -0.0001

Data Index: 1445640 (Python Code)

Max Activating Token Index: 31

Text #6

Max Range: 2.9297. Min Range: -2.9297

Max Act: 2.5484. Min Act: -0.0001

Data Index: 337819 (C4 (Web Text))

Max Activating Token Index: 353

Text #7

Max Range: 2.9297. Min Range: -2.9297

Max Act: 2.2988. Min Act: -0.0000

Data Index: 612236 (C4 (Web Text))

Max Activating Token Index: 297

Text #8

Max Range: 2.9297. Min Range: -2.9297

Max Act: 2.4457. Min Act: -0.0000

Data Index: 807323 (C4 (Web Text))

Max Activating Token Index: 539

Text #9

Max Range: 2.9297. Min Range: -2.9297

Max Act: 2.5665. Min Act: -0.0000

Data Index: 48056 (C4 (Web Text))

Max Activating Token Index: 800

Text #10

Max Range: 2.9297. Min Range: -2.9297

Max Act: 2.3209. Min Act: -0.0000

Data Index: 478498 (C4 (Web Text))

Max Activating Token Index: 734

Text #11

Max Range: 2.9297. Min Range: -2.9297

Max Act: 2.3248. Min Act: -0.0000

Data Index: 1213116 (C4 (Web Text))

Max Activating Token Index: 484

Text #12

Max Range: 2.9297. Min Range: -2.9297

Max Act: 2.4427. Min Act: -0.0000

Data Index: 607242 (C4 (Web Text))

Max Activating Token Index: 718

Text #13

Max Range: 2.9297. Min Range: -2.9297

Max Act: 2.2733. Min Act: -0.0000

Data Index: 1194642 (C4 (Web Text))

Max Activating Token Index: 477

Text #14

Max Range: 2.9297. Min Range: -2.9297

Max Act: 2.2733. Min Act: -0.0000

Data Index: 788864 (C4 (Web Text))

Max Activating Token Index: 159

Text #15

Max Range: 2.9297. Min Range: -2.9297

Max Act: 2.0081. Min Act: -0.0000

Data Index: 902934 (C4 (Web Text))

Max Activating Token Index: 99

Text #16

Max Range: 2.9297. Min Range: -2.9297

Max Act: 2.1919. Min Act: -0.0000

Data Index: 1293431 (C4 (Web Text))

Max Activating Token Index: 422

Text #17

Max Range: 2.9297. Min Range: -2.9297

Max Act: 2.0744. Min Act: -0.0000

Data Index: 1429151 (Python Code)

Max Activating Token Index: 880

Text #18

Max Range: 2.9297. Min Range: -2.9297

Max Act: 2.1538. Min Act: -0.0001

Data Index: 1360339 (Python Code)

Max Activating Token Index: 52

Text #19

Max Range: 2.9297. Min Range: -2.9297

Max Act: 2.1360. Min Act: -0.0001

Data Index: 437017 (C4 (Web Text))

Max Activating Token Index: 217