Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4325 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.8386. Min Act: 0.0000

Data Index: 814299 (C4 (Web Text))

Max Activating Token Index: 194

Text #1

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.6093. Min Act: -0.0000

Data Index: 1632590 (Python Code)

Max Activating Token Index: 689

Text #2

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.5020. Min Act: -0.0000

Data Index: 1585573 (Python Code)

Max Activating Token Index: 319

Text #3

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.4953. Min Act: -0.0000

Data Index: 1383842 (Python Code)

Max Activating Token Index: 374

Text #4

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.4522. Min Act: -0.0000

Data Index: 1418493 (Python Code)

Max Activating Token Index: 399

Text #5

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.3386. Min Act: -0.0000

Data Index: 1145103 (C4 (Web Text))

Max Activating Token Index: 145

Text #6

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.4958. Min Act: -0.0000

Data Index: 1225029 (C4 (Web Text))

Max Activating Token Index: 808

Text #7

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.4900. Min Act: -0.0000

Data Index: 133620 (C4 (Web Text))

Max Activating Token Index: 678

Text #8

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.3644. Min Act: -0.0000

Data Index: 765404 (C4 (Web Text))

Max Activating Token Index: 837

Text #9

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.4529. Min Act: -0.0000

Data Index: 1392567 (Python Code)

Max Activating Token Index: 771

Text #10

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.3365. Min Act: 0.0000

Data Index: 125820 (C4 (Web Text))

Max Activating Token Index: 179

Text #11

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.3207. Min Act: -0.0000

Data Index: 737000 (C4 (Web Text))

Max Activating Token Index: 74

Text #12

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.2999. Min Act: -0.0000

Data Index: 1291022 (C4 (Web Text))

Max Activating Token Index: 123

Text #13

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.3724. Min Act: -0.0000

Data Index: 46808 (C4 (Web Text))

Max Activating Token Index: 341

Text #14

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.2754. Min Act: -0.0000

Data Index: 468557 (C4 (Web Text))

Max Activating Token Index: 363

Text #15

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.2785. Min Act: 0.0000

Data Index: 1212879 (C4 (Web Text))

Max Activating Token Index: 630

Text #16

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.2711. Min Act: -0.0000

Data Index: 37860 (C4 (Web Text))

Max Activating Token Index: 408

Text #17

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.2494. Min Act: -0.0000

Data Index: 168795 (C4 (Web Text))

Max Activating Token Index: 303

Text #18

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.2410. Min Act: -0.0000

Data Index: 902803 (C4 (Web Text))

Max Activating Token Index: 365

Text #19

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.2344. Min Act: 0.0000

Data Index: 515026 (C4 (Web Text))

Max Activating Token Index: 151