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

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

Neuron 4785 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: 1.3246. Min Range: -1.3246

Max Act: 1.3246. Min Act: -0.0000

Data Index: 383807 (C4 (Web Text))

Max Activating Token Index: 144

Text #1

Max Range: 1.3246. Min Range: -1.3246

Max Act: 1.2389. Min Act: -0.0000

Data Index: 858500 (C4 (Web Text))

Max Activating Token Index: 469

Text #2

Max Range: 1.3246. Min Range: -1.3246

Max Act: 1.3051. Min Act: -0.0000

Data Index: 1082543 (C4 (Web Text))

Max Activating Token Index: 665

Text #3

Max Range: 1.3246. Min Range: -1.3246

Max Act: 1.1683. Min Act: -0.0000

Data Index: 1137580 (C4 (Web Text))

Max Activating Token Index: 739

Text #4

Max Range: 1.3246. Min Range: -1.3246

Max Act: 1.2352. Min Act: -0.0000

Data Index: 387644 (C4 (Web Text))

Max Activating Token Index: 603

Text #5

Max Range: 1.3246. Min Range: -1.3246

Max Act: 1.1680. Min Act: -0.0000

Data Index: 350934 (C4 (Web Text))

Max Activating Token Index: 384

Text #6

Max Range: 1.3246. Min Range: -1.3246

Max Act: 1.1663. Min Act: -0.0000

Data Index: 71323 (C4 (Web Text))

Max Activating Token Index: 496

Text #7

Max Range: 1.3246. Min Range: -1.3246

Max Act: 1.1330. Min Act: -0.0000

Data Index: 864458 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 1.3246. Min Range: -1.3246

Max Act: 1.2116. Min Act: -0.0000

Data Index: 1041406 (C4 (Web Text))

Max Activating Token Index: 171

Text #9

Max Range: 1.3246. Min Range: -1.3246

Max Act: 1.1972. Min Act: -0.0000

Data Index: 487699 (C4 (Web Text))

Max Activating Token Index: 152

Text #10

Max Range: 1.3246. Min Range: -1.3246

Max Act: 1.1212. Min Act: -0.0000

Data Index: 1099378 (C4 (Web Text))

Max Activating Token Index: 639

Text #11

Max Range: 1.3246. Min Range: -1.3246

Max Act: 1.0764. Min Act: -0.0000

Data Index: 595179 (C4 (Web Text))

Max Activating Token Index: 632

Text #12

Max Range: 1.3246. Min Range: -1.3246

Max Act: 1.1365. Min Act: -0.0000

Data Index: 1202612 (C4 (Web Text))

Max Activating Token Index: 308

Text #13

Max Range: 1.3246. Min Range: -1.3246

Max Act: 1.1605. Min Act: -0.0000

Data Index: 166965 (C4 (Web Text))

Max Activating Token Index: 733

Text #14

Max Range: 1.3246. Min Range: -1.3246

Max Act: 1.1684. Min Act: -0.0000

Data Index: 80356 (C4 (Web Text))

Max Activating Token Index: 463

Text #15

Max Range: 1.3246. Min Range: -1.3246

Max Act: 1.1533. Min Act: -0.0000

Data Index: 560578 (C4 (Web Text))

Max Activating Token Index: 502

Text #16

Max Range: 1.3246. Min Range: -1.3246

Max Act: 1.1406. Min Act: -0.0000

Data Index: 392851 (C4 (Web Text))

Max Activating Token Index: 176

Text #17

Max Range: 1.3246. Min Range: -1.3246

Max Act: 1.1248. Min Act: -0.0000

Data Index: 581653 (C4 (Web Text))

Max Activating Token Index: 317

Text #18

Max Range: 1.3246. Min Range: -1.3246

Max Act: 1.0940. Min Act: -0.0000

Data Index: 118731 (C4 (Web Text))

Max Activating Token Index: 937

Text #19

Max Range: 1.3246. Min Range: -1.3246

Max Act: 1.1120. Min Act: -0.0000

Data Index: 920589 (C4 (Web Text))

Max Activating Token Index: 116