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

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

Neuron 3926 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6497. Min Range: -2.6497

Max Act: 2.6497. Min Act: -0.0000

Data Index: 733306 (C4 (Web Text))

Max Activating Token Index: 470

Text #1

Max Range: 2.6497. Min Range: -2.6497

Max Act: 1.9570. Min Act: -0.0000

Data Index: 388875 (C4 (Web Text))

Max Activating Token Index: 566

Text #2

Max Range: 2.6497. Min Range: -2.6497

Max Act: 1.9508. Min Act: -0.0000

Data Index: 1316220 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 2.6497. Min Range: -2.6497

Max Act: 1.9027. Min Act: -0.0000

Data Index: 1195801 (C4 (Web Text))

Max Activating Token Index: 506

Text #4

Max Range: 2.6497. Min Range: -2.6497

Max Act: 1.8849. Min Act: -0.0000

Data Index: 1169556 (C4 (Web Text))

Max Activating Token Index: 436

Text #5

Max Range: 2.6497. Min Range: -2.6497

Max Act: 1.9555. Min Act: -0.0000

Data Index: 211321 (C4 (Web Text))

Max Activating Token Index: 32

Text #6

Max Range: 2.6497. Min Range: -2.6497

Max Act: 1.8231. Min Act: -0.0000

Data Index: 399798 (C4 (Web Text))

Max Activating Token Index: 586

Text #7

Max Range: 2.6497. Min Range: -2.6497

Max Act: 1.7086. Min Act: -0.0000

Data Index: 1195554 (C4 (Web Text))

Max Activating Token Index: 596

Text #8

Max Range: 2.6497. Min Range: -2.6497

Max Act: 1.6687. Min Act: -0.0000

Data Index: 608592 (C4 (Web Text))

Max Activating Token Index: 557

Text #9

Max Range: 2.6497. Min Range: -2.6497

Max Act: 1.6543. Min Act: -0.0000

Data Index: 708827 (C4 (Web Text))

Max Activating Token Index: 134

Text #10

Max Range: 2.6497. Min Range: -2.6497

Max Act: 1.7426. Min Act: -0.0000

Data Index: 1323662 (C4 (Web Text))

Max Activating Token Index: 583

Text #11

Max Range: 2.6497. Min Range: -2.6497

Max Act: 1.7201. Min Act: -0.0000

Data Index: 853797 (C4 (Web Text))

Max Activating Token Index: 869

Text #12

Max Range: 2.6497. Min Range: -2.6497

Max Act: 1.7733. Min Act: -0.0000

Data Index: 1229632 (C4 (Web Text))

Max Activating Token Index: 287

Text #13

Max Range: 2.6497. Min Range: -2.6497

Max Act: 1.6474. Min Act: -0.0000

Data Index: 857415 (C4 (Web Text))

Max Activating Token Index: 875

Text #14

Max Range: 2.6497. Min Range: -2.6497

Max Act: 1.5960. Min Act: -0.0000

Data Index: 454250 (C4 (Web Text))

Max Activating Token Index: 385

Text #15

Max Range: 2.6497. Min Range: -2.6497

Max Act: 1.5360. Min Act: -0.0000

Data Index: 458427 (C4 (Web Text))

Max Activating Token Index: 534

Text #16

Max Range: 2.6497. Min Range: -2.6497

Max Act: 1.5401. Min Act: -0.0000

Data Index: 554970 (C4 (Web Text))

Max Activating Token Index: 257

Text #17

Max Range: 2.6497. Min Range: -2.6497

Max Act: 1.5935. Min Act: -0.0000

Data Index: 942295 (C4 (Web Text))

Max Activating Token Index: 625

Text #18

Max Range: 2.6497. Min Range: -2.6497

Max Act: 1.4918. Min Act: -0.0000

Data Index: 769491 (C4 (Web Text))

Max Activating Token Index: 99

Text #19

Max Range: 2.6497. Min Range: -2.6497

Max Act: 1.5055. Min Act: -0.0000

Data Index: 1166470 (C4 (Web Text))

Max Activating Token Index: 203