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

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

Neuron 4216 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: 1.0783. Min Range: -1.0783

Max Act: 1.0783. Min Act: -0.0000

Data Index: 10473 (C4 (Web Text))

Max Activating Token Index: 839

Text #1

Max Range: 1.0783. Min Range: -1.0783

Max Act: 0.7332. Min Act: -0.0000

Data Index: 389860 (C4 (Web Text))

Max Activating Token Index: 141

Text #2

Max Range: 1.0783. Min Range: -1.0783

Max Act: 0.7076. Min Act: -0.0000

Data Index: 965426 (C4 (Web Text))

Max Activating Token Index: 240

Text #3

Max Range: 1.0783. Min Range: -1.0783

Max Act: 0.5940. Min Act: -0.0000

Data Index: 338212 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 1.0783. Min Range: -1.0783

Max Act: 0.6336. Min Act: -0.0000

Data Index: 1321624 (C4 (Web Text))

Max Activating Token Index: 270

Text #5

Max Range: 1.0783. Min Range: -1.0783

Max Act: 0.6397. Min Act: -0.0000

Data Index: 697306 (C4 (Web Text))

Max Activating Token Index: 424

Text #6

Max Range: 1.0783. Min Range: -1.0783

Max Act: 0.5851. Min Act: -0.0000

Data Index: 1309776 (C4 (Web Text))

Max Activating Token Index: 474

Text #7

Max Range: 1.0783. Min Range: -1.0783

Max Act: 0.5958. Min Act: -0.0000

Data Index: 795840 (C4 (Web Text))

Max Activating Token Index: 800

Text #8

Max Range: 1.0783. Min Range: -1.0783

Max Act: 0.5738. Min Act: -0.0000

Data Index: 791251 (C4 (Web Text))

Max Activating Token Index: 521

Text #9

Max Range: 1.0783. Min Range: -1.0783

Max Act: 0.5840. Min Act: -0.0000

Data Index: 506065 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 1.0783. Min Range: -1.0783

Max Act: 0.5792. Min Act: -0.0000

Data Index: 1447196 (Python Code)

Max Activating Token Index: 395

Text #11

Max Range: 1.0783. Min Range: -1.0783

Max Act: 0.5579. Min Act: -0.0000

Data Index: 1330416 (C4 (Web Text))

Max Activating Token Index: 36

Text #12

Max Range: 1.0783. Min Range: -1.0783

Max Act: 0.5849. Min Act: -0.0000

Data Index: 1266364 (C4 (Web Text))

Max Activating Token Index: 245

Text #13

Max Range: 1.0783. Min Range: -1.0783

Max Act: 0.5530. Min Act: -0.0000

Data Index: 1216588 (C4 (Web Text))

Max Activating Token Index: 959

Text #14

Max Range: 1.0783. Min Range: -1.0783

Max Act: 0.5337. Min Act: -0.0000

Data Index: 1356195 (C4 (Web Text))

Max Activating Token Index: 224

Text #15

Max Range: 1.0783. Min Range: -1.0783

Max Act: 0.5704. Min Act: -0.0000

Data Index: 1067114 (C4 (Web Text))

Max Activating Token Index: 783

Text #16

Max Range: 1.0783. Min Range: -1.0783

Max Act: 0.5636. Min Act: -0.0000

Data Index: 1454292 (Python Code)

Max Activating Token Index: 363

Text #17

Max Range: 1.0783. Min Range: -1.0783

Max Act: 0.5964. Min Act: -0.0000

Data Index: 248904 (C4 (Web Text))

Max Activating Token Index: 702

Text #18

Max Range: 1.0783. Min Range: -1.0783

Max Act: 0.5435. Min Act: -0.0000

Data Index: 1221746 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 1.0783. Min Range: -1.0783

Max Act: 0.4922. Min Act: -0.0000

Data Index: 1005841 (C4 (Web Text))

Max Activating Token Index: 831