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

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

Neuron 5942 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.5718. Min Act: -0.0000

Data Index: 1040468 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.3831. Min Act: -0.0000

Data Index: 1309981 (C4 (Web Text))

Max Activating Token Index: 269

Text #2

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.3537. Min Act: -0.0000

Data Index: 628175 (C4 (Web Text))

Max Activating Token Index: 876

Text #3

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.2852. Min Act: -0.0000

Data Index: 132178 (C4 (Web Text))

Max Activating Token Index: 615

Text #4

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.2911. Min Act: -0.0000

Data Index: 135602 (C4 (Web Text))

Max Activating Token Index: 520

Text #5

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.2653. Min Act: -0.0000

Data Index: 1085218 (C4 (Web Text))

Max Activating Token Index: 471

Text #6

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.2738. Min Act: -0.0000

Data Index: 746777 (C4 (Web Text))

Max Activating Token Index: 927

Text #7

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.2456. Min Act: -0.0000

Data Index: 46952 (C4 (Web Text))

Max Activating Token Index: 809

Text #8

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.2460. Min Act: -0.0000

Data Index: 768724 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.2294. Min Act: -0.0000

Data Index: 926458 (C4 (Web Text))

Max Activating Token Index: 519

Text #10

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.2431. Min Act: -0.0000

Data Index: 880185 (C4 (Web Text))

Max Activating Token Index: 609

Text #11

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.2298. Min Act: -0.0000

Data Index: 352892 (C4 (Web Text))

Max Activating Token Index: 419

Text #12

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.2531. Min Act: -0.0000

Data Index: 26904 (C4 (Web Text))

Max Activating Token Index: 670

Text #13

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.2403. Min Act: -0.0000

Data Index: 291764 (C4 (Web Text))

Max Activating Token Index: 262

Text #14

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.2194. Min Act: -0.0000

Data Index: 583454 (C4 (Web Text))

Max Activating Token Index: 917

Text #15

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.2232. Min Act: -0.0000

Data Index: 439567 (C4 (Web Text))

Max Activating Token Index: 378

Text #16

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.2710. Min Act: -0.0000

Data Index: 927020 (C4 (Web Text))

Max Activating Token Index: 866

Text #17

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.2074. Min Act: -0.0000

Data Index: 440465 (C4 (Web Text))

Max Activating Token Index: 754

Text #18

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.2487. Min Act: -0.0000

Data Index: 939869 (C4 (Web Text))

Max Activating Token Index: 160

Text #19

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.2453. Min Act: -0.0000

Data Index: 749922 (C4 (Web Text))

Max Activating Token Index: 678