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

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

Neuron 3451 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 9.0615. Min Range: -9.0615

Max Act: 9.0428. Min Act: -0.0000

Data Index: 175448 (C4 (Web Text))

Max Activating Token Index: 80

Text #1

Max Range: 9.0615. Min Range: -9.0615

Max Act: 8.8116. Min Act: -0.0001

Data Index: 197597 (C4 (Web Text))

Max Activating Token Index: 293

Text #2

Max Range: 9.0615. Min Range: -9.0615

Max Act: 9.0615. Min Act: -0.0000

Data Index: 469787 (C4 (Web Text))

Max Activating Token Index: 335

Text #3

Max Range: 9.0615. Min Range: -9.0615

Max Act: 7.6490. Min Act: -0.0000

Data Index: 521948 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 9.0615. Min Range: -9.0615

Max Act: 7.0671. Min Act: -0.0001

Data Index: 166737 (C4 (Web Text))

Max Activating Token Index: 141

Text #5

Max Range: 9.0615. Min Range: -9.0615

Max Act: 7.1433. Min Act: -0.0000

Data Index: 1184373 (C4 (Web Text))

Max Activating Token Index: 310

Text #6

Max Range: 9.0615. Min Range: -9.0615

Max Act: 6.7335. Min Act: -0.0000

Data Index: 300069 (C4 (Web Text))

Max Activating Token Index: 675

Text #7

Max Range: 9.0615. Min Range: -9.0615

Max Act: 6.7937. Min Act: -0.0000

Data Index: 546947 (C4 (Web Text))

Max Activating Token Index: 891

Text #8

Max Range: 9.0615. Min Range: -9.0615

Max Act: 6.4782. Min Act: -0.0000

Data Index: 1213788 (C4 (Web Text))

Max Activating Token Index: 42

Text #9

Max Range: 9.0615. Min Range: -9.0615

Max Act: 6.0856. Min Act: -0.0000

Data Index: 98542 (C4 (Web Text))

Max Activating Token Index: 419

Text #10

Max Range: 9.0615. Min Range: -9.0615

Max Act: 6.2476. Min Act: -0.0000

Data Index: 497613 (C4 (Web Text))

Max Activating Token Index: 180

Text #11

Max Range: 9.0615. Min Range: -9.0615

Max Act: 5.9858. Min Act: -0.0000

Data Index: 1216487 (C4 (Web Text))

Max Activating Token Index: 382

Text #12

Max Range: 9.0615. Min Range: -9.0615

Max Act: 6.3025. Min Act: -0.0000

Data Index: 1222382 (C4 (Web Text))

Max Activating Token Index: 607

Text #13

Max Range: 9.0615. Min Range: -9.0615

Max Act: 6.5504. Min Act: -0.0001

Data Index: 839212 (C4 (Web Text))

Max Activating Token Index: 604

Text #14

Max Range: 9.0615. Min Range: -9.0615

Max Act: 6.6588. Min Act: -0.0001

Data Index: 165548 (C4 (Web Text))

Max Activating Token Index: 403

Text #15

Max Range: 9.0615. Min Range: -9.0615

Max Act: 6.0913. Min Act: -0.0000

Data Index: 325510 (C4 (Web Text))

Max Activating Token Index: 387

Text #16

Max Range: 9.0615. Min Range: -9.0615

Max Act: 6.4231. Min Act: -0.0001

Data Index: 470186 (C4 (Web Text))

Max Activating Token Index: 294

Text #17

Max Range: 9.0615. Min Range: -9.0615

Max Act: 6.0145. Min Act: -0.0001

Data Index: 1178820 (C4 (Web Text))

Max Activating Token Index: 651

Text #18

Max Range: 9.0615. Min Range: -9.0615

Max Act: 6.1660. Min Act: -0.0000

Data Index: 1148689 (C4 (Web Text))

Max Activating Token Index: 129

Text #19

Max Range: 9.0615. Min Range: -9.0615

Max Act: 6.3432. Min Act: -0.0001

Data Index: 333733 (C4 (Web Text))

Max Activating Token Index: 471