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

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

Neuron 532 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7702. Min Range: -0.7702

Max Act: 0.7702. Min Act: -0.0000

Data Index: 389528 (C4 (Web Text))

Max Activating Token Index: 1011

Text #1

Max Range: 0.7702. Min Range: -0.7702

Max Act: 0.7048. Min Act: -0.0000

Data Index: 357107 (C4 (Web Text))

Max Activating Token Index: 109

Text #2

Max Range: 0.7702. Min Range: -0.7702

Max Act: 0.6499. Min Act: -0.0000

Data Index: 903947 (C4 (Web Text))

Max Activating Token Index: 88

Text #3

Max Range: 0.7702. Min Range: -0.7702

Max Act: 0.5716. Min Act: -0.0000

Data Index: 1020931 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.7702. Min Range: -0.7702

Max Act: 0.6199. Min Act: -0.0000

Data Index: 1117471 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 0.7702. Min Range: -0.7702

Max Act: 0.6495. Min Act: -0.0000

Data Index: 1126902 (C4 (Web Text))

Max Activating Token Index: 681

Text #6

Max Range: 0.7702. Min Range: -0.7702

Max Act: 0.5778. Min Act: -0.0000

Data Index: 670581 (C4 (Web Text))

Max Activating Token Index: 478

Text #7

Max Range: 0.7702. Min Range: -0.7702

Max Act: 0.6112. Min Act: -0.0000

Data Index: 1319887 (C4 (Web Text))

Max Activating Token Index: 266

Text #8

Max Range: 0.7702. Min Range: -0.7702

Max Act: 0.5548. Min Act: -0.0000

Data Index: 409371 (C4 (Web Text))

Max Activating Token Index: 628

Text #9

Max Range: 0.7702. Min Range: -0.7702

Max Act: 0.5406. Min Act: -0.0000

Data Index: 857527 (C4 (Web Text))

Max Activating Token Index: 486

Text #10

Max Range: 0.7702. Min Range: -0.7702

Max Act: 0.5581. Min Act: -0.0000

Data Index: 800332 (C4 (Web Text))

Max Activating Token Index: 360

Text #11

Max Range: 0.7702. Min Range: -0.7702

Max Act: 0.5511. Min Act: -0.0000

Data Index: 795044 (C4 (Web Text))

Max Activating Token Index: 176

Text #12

Max Range: 0.7702. Min Range: -0.7702

Max Act: 0.5583. Min Act: -0.0000

Data Index: 1248111 (C4 (Web Text))

Max Activating Token Index: 658

Text #13

Max Range: 0.7702. Min Range: -0.7702

Max Act: 0.5161. Min Act: -0.0000

Data Index: 564816 (C4 (Web Text))

Max Activating Token Index: 280

Text #14

Max Range: 0.7702. Min Range: -0.7702

Max Act: 0.5337. Min Act: -0.0000

Data Index: 506363 (C4 (Web Text))

Max Activating Token Index: 362

Text #15

Max Range: 0.7702. Min Range: -0.7702

Max Act: 0.5199. Min Act: -0.0000

Data Index: 62234 (C4 (Web Text))

Max Activating Token Index: 544

Text #16

Max Range: 0.7702. Min Range: -0.7702

Max Act: 0.5421. Min Act: -0.0000

Data Index: 1284035 (C4 (Web Text))

Max Activating Token Index: 872

Text #17

Max Range: 0.7702. Min Range: -0.7702

Max Act: 0.5089. Min Act: -0.0000

Data Index: 80993 (C4 (Web Text))

Max Activating Token Index: 453

Text #18

Max Range: 0.7702. Min Range: -0.7702

Max Act: 0.4964. Min Act: -0.0000

Data Index: 1163090 (C4 (Web Text))

Max Activating Token Index: 577

Text #19

Max Range: 0.7702. Min Range: -0.7702

Max Act: 0.4937. Min Act: -0.0000

Data Index: 1178532 (C4 (Web Text))

Max Activating Token Index: 337