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

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

Neuron 594 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6120. Min Range: -2.6120

Max Act: 2.6120. Min Act: -0.0000

Data Index: 947944 (C4 (Web Text))

Max Activating Token Index: 679

Text #1

Max Range: 2.6120. Min Range: -2.6120

Max Act: 1.8977. Min Act: -0.0000

Data Index: 924645 (C4 (Web Text))

Max Activating Token Index: 377

Text #2

Max Range: 2.6120. Min Range: -2.6120

Max Act: 1.8421. Min Act: -0.0000

Data Index: 747262 (C4 (Web Text))

Max Activating Token Index: 404

Text #3

Max Range: 2.6120. Min Range: -2.6120

Max Act: 1.8130. Min Act: -0.0000

Data Index: 1333073 (C4 (Web Text))

Max Activating Token Index: 120

Text #4

Max Range: 2.6120. Min Range: -2.6120

Max Act: 1.7660. Min Act: -0.0000

Data Index: 577673 (C4 (Web Text))

Max Activating Token Index: 300

Text #5

Max Range: 2.6120. Min Range: -2.6120

Max Act: 1.7286. Min Act: -0.0000

Data Index: 392250 (C4 (Web Text))

Max Activating Token Index: 576

Text #6

Max Range: 2.6120. Min Range: -2.6120

Max Act: 1.7280. Min Act: -0.0000

Data Index: 181776 (C4 (Web Text))

Max Activating Token Index: 336

Text #7

Max Range: 2.6120. Min Range: -2.6120

Max Act: 1.5891. Min Act: -0.0000

Data Index: 1146200 (C4 (Web Text))

Max Activating Token Index: 715

Text #8

Max Range: 2.6120. Min Range: -2.6120

Max Act: 1.5707. Min Act: -0.0000

Data Index: 1187685 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 2.6120. Min Range: -2.6120

Max Act: 1.5723. Min Act: -0.0000

Data Index: 1388984 (Python Code)

Max Activating Token Index: 361

Text #10

Max Range: 2.6120. Min Range: -2.6120

Max Act: 1.6577. Min Act: -0.0000

Data Index: 703955 (C4 (Web Text))

Max Activating Token Index: 1011

Text #11

Max Range: 2.6120. Min Range: -2.6120

Max Act: 1.6534. Min Act: -0.0000

Data Index: 552880 (C4 (Web Text))

Max Activating Token Index: 785

Text #12

Max Range: 2.6120. Min Range: -2.6120

Max Act: 1.7511. Min Act: -0.0000

Data Index: 1480643 (Python Code)

Max Activating Token Index: 378

Text #13

Max Range: 2.6120. Min Range: -2.6120

Max Act: 1.6172. Min Act: -0.0000

Data Index: 80318 (C4 (Web Text))

Max Activating Token Index: 549

Text #14

Max Range: 2.6120. Min Range: -2.6120

Max Act: 1.7157. Min Act: -0.0000

Data Index: 1332346 (C4 (Web Text))

Max Activating Token Index: 519

Text #15

Max Range: 2.6120. Min Range: -2.6120

Max Act: 1.6131. Min Act: -0.0000

Data Index: 1000713 (C4 (Web Text))

Max Activating Token Index: 350

Text #16

Max Range: 2.6120. Min Range: -2.6120

Max Act: 1.6978. Min Act: -0.0000

Data Index: 1539560 (Python Code)

Max Activating Token Index: 769

Text #17

Max Range: 2.6120. Min Range: -2.6120

Max Act: 1.6899. Min Act: -0.0000

Data Index: 176260 (C4 (Web Text))

Max Activating Token Index: 923

Text #18

Max Range: 2.6120. Min Range: -2.6120

Max Act: 1.4821. Min Act: -0.0000

Data Index: 1623479 (Python Code)

Max Activating Token Index: 398

Text #19

Max Range: 2.6120. Min Range: -2.6120

Max Act: 1.5095. Min Act: -0.0000

Data Index: 778462 (C4 (Web Text))

Max Activating Token Index: 252