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

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

Neuron 495 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: 0.4968. Min Range: -0.4968

Max Act: 0.4902. Min Act: -0.0000

Data Index: 49901 (C4 (Web Text))

Max Activating Token Index: 318

Text #1

Max Range: 0.4968. Min Range: -0.4968

Max Act: 0.4854. Min Act: 0.0000

Data Index: 292649 (C4 (Web Text))

Max Activating Token Index: 300

Text #2

Max Range: 0.4968. Min Range: -0.4968

Max Act: 0.4621. Min Act: -0.0000

Data Index: 1476922 (Python Code)

Max Activating Token Index: 765

Text #3

Max Range: 0.4968. Min Range: -0.4968

Max Act: 0.4968. Min Act: -0.0000

Data Index: 1387575 (Python Code)

Max Activating Token Index: 528

Text #4

Max Range: 0.4968. Min Range: -0.4968

Max Act: 0.4557. Min Act: -0.0000

Data Index: 433108 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 0.4968. Min Range: -0.4968

Max Act: 0.4364. Min Act: -0.0000

Data Index: 996749 (C4 (Web Text))

Max Activating Token Index: 887

Text #6

Max Range: 0.4968. Min Range: -0.4968

Max Act: 0.4570. Min Act: -0.0000

Data Index: 486130 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 0.4968. Min Range: -0.4968

Max Act: 0.4369. Min Act: -0.0000

Data Index: 496866 (C4 (Web Text))

Max Activating Token Index: 318

Text #8

Max Range: 0.4968. Min Range: -0.4968

Max Act: 0.3868. Min Act: -0.0000

Data Index: 1626077 (Python Code)

Max Activating Token Index: 859

Text #9

Max Range: 0.4968. Min Range: -0.4968

Max Act: 0.3918. Min Act: -0.0000

Data Index: 903797 (C4 (Web Text))

Max Activating Token Index: 164

Text #10

Max Range: 0.4968. Min Range: -0.4968

Max Act: 0.4018. Min Act: -0.0000

Data Index: 746772 (C4 (Web Text))

Max Activating Token Index: 591

Text #11

Max Range: 0.4968. Min Range: -0.4968

Max Act: 0.3830. Min Act: -0.0000

Data Index: 166501 (C4 (Web Text))

Max Activating Token Index: 638

Text #12

Max Range: 0.4968. Min Range: -0.4968

Max Act: 0.3813. Min Act: -0.0000

Data Index: 194090 (C4 (Web Text))

Max Activating Token Index: 627

Text #13

Max Range: 0.4968. Min Range: -0.4968

Max Act: 0.3905. Min Act: -0.0000

Data Index: 923849 (C4 (Web Text))

Max Activating Token Index: 47

Text #14

Max Range: 0.4968. Min Range: -0.4968

Max Act: 0.3718. Min Act: 0.0001

Data Index: 117235 (C4 (Web Text))

Max Activating Token Index: 413

Text #15

Max Range: 0.4968. Min Range: -0.4968

Max Act: 0.3630. Min Act: -0.0000

Data Index: 684979 (C4 (Web Text))

Max Activating Token Index: 185

Text #16

Max Range: 0.4968. Min Range: -0.4968

Max Act: 0.3631. Min Act: 0.0001

Data Index: 1120711 (C4 (Web Text))

Max Activating Token Index: 497

Text #17

Max Range: 0.4968. Min Range: -0.4968

Max Act: 0.3541. Min Act: -0.0000

Data Index: 1222537 (C4 (Web Text))

Max Activating Token Index: 68

Text #18

Max Range: 0.4968. Min Range: -0.4968

Max Act: 0.3383. Min Act: -0.0000

Data Index: 1301310 (C4 (Web Text))

Max Activating Token Index: 954

Text #19

Max Range: 0.4968. Min Range: -0.4968

Max Act: 0.3491. Min Act: 0.0001

Data Index: 328503 (C4 (Web Text))

Max Activating Token Index: 949