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

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

Neuron 4398 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1421. Min Range: -2.1421

Max Act: 2.0442. Min Act: -0.0000

Data Index: 35752 (C4 (Web Text))

Max Activating Token Index: 591

Text #1

Max Range: 2.1421. Min Range: -2.1421

Max Act: 2.1421. Min Act: -0.0000

Data Index: 1124372 (C4 (Web Text))

Max Activating Token Index: 463

Text #2

Max Range: 2.1421. Min Range: -2.1421

Max Act: 2.0006. Min Act: -0.0000

Data Index: 1250967 (C4 (Web Text))

Max Activating Token Index: 153

Text #3

Max Range: 2.1421. Min Range: -2.1421

Max Act: 1.9440. Min Act: -0.0001

Data Index: 1358411 (C4 (Web Text))

Max Activating Token Index: 56

Text #4

Max Range: 2.1421. Min Range: -2.1421

Max Act: 1.7840. Min Act: -0.0000

Data Index: 486508 (C4 (Web Text))

Max Activating Token Index: 557

Text #5

Max Range: 2.1421. Min Range: -2.1421

Max Act: 1.4807. Min Act: -0.0000

Data Index: 372128 (C4 (Web Text))

Max Activating Token Index: 779

Text #6

Max Range: 2.1421. Min Range: -2.1421

Max Act: 1.9566. Min Act: -0.0000

Data Index: 1198470 (C4 (Web Text))

Max Activating Token Index: 756

Text #7

Max Range: 2.1421. Min Range: -2.1421

Max Act: 1.8321. Min Act: -0.0000

Data Index: 371358 (C4 (Web Text))

Max Activating Token Index: 517

Text #8

Max Range: 2.1421. Min Range: -2.1421

Max Act: 1.7131. Min Act: -0.0001

Data Index: 148470 (C4 (Web Text))

Max Activating Token Index: 40

Text #9

Max Range: 2.1421. Min Range: -2.1421

Max Act: 1.7045. Min Act: -0.0000

Data Index: 937388 (C4 (Web Text))

Max Activating Token Index: 431

Text #10

Max Range: 2.1421. Min Range: -2.1421

Max Act: 1.6295. Min Act: -0.0000

Data Index: 1326724 (C4 (Web Text))

Max Activating Token Index: 836

Text #11

Max Range: 2.1421. Min Range: -2.1421

Max Act: 1.4506. Min Act: -0.0000

Data Index: 16485 (C4 (Web Text))

Max Activating Token Index: 1018

Text #12

Max Range: 2.1421. Min Range: -2.1421

Max Act: 1.5390. Min Act: -0.0000

Data Index: 625747 (C4 (Web Text))

Max Activating Token Index: 518

Text #13

Max Range: 2.1421. Min Range: -2.1421

Max Act: 1.5704. Min Act: -0.0000

Data Index: 1300233 (C4 (Web Text))

Max Activating Token Index: 373

Text #14

Max Range: 2.1421. Min Range: -2.1421

Max Act: 1.5058. Min Act: -0.0000

Data Index: 440415 (C4 (Web Text))

Max Activating Token Index: 983

Text #15

Max Range: 2.1421. Min Range: -2.1421

Max Act: 1.5443. Min Act: -0.0000

Data Index: 1130344 (C4 (Web Text))

Max Activating Token Index: 1000

Text #16

Max Range: 2.1421. Min Range: -2.1421

Max Act: 1.5281. Min Act: -0.0000

Data Index: 964348 (C4 (Web Text))

Max Activating Token Index: 66

Text #17

Max Range: 2.1421. Min Range: -2.1421

Max Act: 1.5252. Min Act: -0.0000

Data Index: 765365 (C4 (Web Text))

Max Activating Token Index: 519

Text #18

Max Range: 2.1421. Min Range: -2.1421

Max Act: 1.6050. Min Act: -0.0000

Data Index: 387577 (C4 (Web Text))

Max Activating Token Index: 493

Text #19

Max Range: 2.1421. Min Range: -2.1421

Max Act: 1.4972. Min Act: -0.0000

Data Index: 510785 (C4 (Web Text))

Max Activating Token Index: 450