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

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

Neuron 4589 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3997. Min Range: -1.3997

Max Act: 1.3636. Min Act: -0.0001

Data Index: 282813 (C4 (Web Text))

Max Activating Token Index: 678

Text #1

Max Range: 1.3997. Min Range: -1.3997

Max Act: 1.3997. Min Act: -0.0001

Data Index: 1004216 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 1.3997. Min Range: -1.3997

Max Act: 1.2801. Min Act: -0.0001

Data Index: 1312415 (C4 (Web Text))

Max Activating Token Index: 433

Text #3

Max Range: 1.3997. Min Range: -1.3997

Max Act: 1.2962. Min Act: -0.0001

Data Index: 957469 (C4 (Web Text))

Max Activating Token Index: 372

Text #4

Max Range: 1.3997. Min Range: -1.3997

Max Act: 1.2650. Min Act: -0.0001

Data Index: 181671 (C4 (Web Text))

Max Activating Token Index: 697

Text #5

Max Range: 1.3997. Min Range: -1.3997

Max Act: 1.2277. Min Act: -0.0001

Data Index: 148305 (C4 (Web Text))

Max Activating Token Index: 523

Text #6

Max Range: 1.3997. Min Range: -1.3997

Max Act: 1.2544. Min Act: -0.0001

Data Index: 678979 (C4 (Web Text))

Max Activating Token Index: 748

Text #7

Max Range: 1.3997. Min Range: -1.3997

Max Act: 1.1992. Min Act: -0.0001

Data Index: 130345 (C4 (Web Text))

Max Activating Token Index: 764

Text #8

Max Range: 1.3997. Min Range: -1.3997

Max Act: 1.0998. Min Act: -0.0001

Data Index: 221243 (C4 (Web Text))

Max Activating Token Index: 653

Text #9

Max Range: 1.3997. Min Range: -1.3997

Max Act: 1.1736. Min Act: -0.0001

Data Index: 1075564 (C4 (Web Text))

Max Activating Token Index: 476

Text #10

Max Range: 1.3997. Min Range: -1.3997

Max Act: 1.2468. Min Act: -0.0001

Data Index: 962138 (C4 (Web Text))

Max Activating Token Index: 436

Text #11

Max Range: 1.3997. Min Range: -1.3997

Max Act: 1.1744. Min Act: -0.0001

Data Index: 451252 (C4 (Web Text))

Max Activating Token Index: 439

Text #12

Max Range: 1.3997. Min Range: -1.3997

Max Act: 1.1462. Min Act: -0.0001

Data Index: 286892 (C4 (Web Text))

Max Activating Token Index: 320

Text #13

Max Range: 1.3997. Min Range: -1.3997

Max Act: 1.3709. Min Act: -0.0001

Data Index: 1342595 (C4 (Web Text))

Max Activating Token Index: 1019

Text #14

Max Range: 1.3997. Min Range: -1.3997

Max Act: 1.1978. Min Act: -0.0001

Data Index: 547902 (C4 (Web Text))

Max Activating Token Index: 666

Text #15

Max Range: 1.3997. Min Range: -1.3997

Max Act: 1.1519. Min Act: -0.0001

Data Index: 811357 (C4 (Web Text))

Max Activating Token Index: 874

Text #16

Max Range: 1.3997. Min Range: -1.3997

Max Act: 1.1454. Min Act: -0.0001

Data Index: 591056 (C4 (Web Text))

Max Activating Token Index: 674

Text #17

Max Range: 1.3997. Min Range: -1.3997

Max Act: 1.1962. Min Act: -0.0001

Data Index: 1341982 (C4 (Web Text))

Max Activating Token Index: 432

Text #18

Max Range: 1.3997. Min Range: -1.3997

Max Act: 1.1595. Min Act: -0.0001

Data Index: 768096 (C4 (Web Text))

Max Activating Token Index: 473

Text #19

Max Range: 1.3997. Min Range: -1.3997

Max Act: 1.1522. Min Act: -0.0001

Data Index: 74938 (C4 (Web Text))

Max Activating Token Index: 378