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

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

Neuron 4920 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: 0.3453. Min Range: -0.3453

Max Act: 0.3453. Min Act: -0.0000

Data Index: 1577292 (Python Code)

Max Activating Token Index: 544

Text #1

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.3141. Min Act: -0.0000

Data Index: 37576 (C4 (Web Text))

Max Activating Token Index: 971

Text #2

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.3294. Min Act: -0.0000

Data Index: 511361 (C4 (Web Text))

Max Activating Token Index: 240

Text #3

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.3077. Min Act: -0.0000

Data Index: 315372 (C4 (Web Text))

Max Activating Token Index: 705

Text #4

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.3007. Min Act: 0.0000

Data Index: 1338714 (C4 (Web Text))

Max Activating Token Index: 870

Text #5

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.2939. Min Act: -0.0000

Data Index: 1558516 (Python Code)

Max Activating Token Index: 1011

Text #6

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.2808. Min Act: -0.0000

Data Index: 1479195 (Python Code)

Max Activating Token Index: 509

Text #7

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.2893. Min Act: -0.0000

Data Index: 1411923 (Python Code)

Max Activating Token Index: 929

Text #8

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.2791. Min Act: -0.0000

Data Index: 1491120 (Python Code)

Max Activating Token Index: 527

Text #9

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.2699. Min Act: -0.0000

Data Index: 988788 (C4 (Web Text))

Max Activating Token Index: 111

Text #10

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.2652. Min Act: -0.0000

Data Index: 1452592 (Python Code)

Max Activating Token Index: 987

Text #11

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.2757. Min Act: -0.0000

Data Index: 1654864 (Python Code)

Max Activating Token Index: 627

Text #12

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.2669. Min Act: -0.0000

Data Index: 1571277 (Python Code)

Max Activating Token Index: 940

Text #13

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.2811. Min Act: -0.0000

Data Index: 1500444 (Python Code)

Max Activating Token Index: 851

Text #14

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.2702. Min Act: -0.0000

Data Index: 1458275 (Python Code)

Max Activating Token Index: 963

Text #15

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.2589. Min Act: -0.0000

Data Index: 299954 (C4 (Web Text))

Max Activating Token Index: 736

Text #16

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.2660. Min Act: -0.0000

Data Index: 1509773 (Python Code)

Max Activating Token Index: 696

Text #17

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.2637. Min Act: -0.0000

Data Index: 1560216 (Python Code)

Max Activating Token Index: 910

Text #18

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.2454. Min Act: -0.0000

Data Index: 932133 (C4 (Web Text))

Max Activating Token Index: 193

Text #19

Max Range: 0.3453. Min Range: -0.3453

Max Act: 0.2575. Min Act: -0.0000

Data Index: 1510471 (Python Code)

Max Activating Token Index: 427