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

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

Neuron 323 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: 0.4567. Min Range: -0.4567

Max Act: 0.4567. Min Act: -0.0000

Data Index: 170884 (C4 (Web Text))

Max Activating Token Index: 872

Text #1

Max Range: 0.4567. Min Range: -0.4567

Max Act: 0.4426. Min Act: -0.0000

Data Index: 748899 (C4 (Web Text))

Max Activating Token Index: 620

Text #2

Max Range: 0.4567. Min Range: -0.4567

Max Act: 0.3779. Min Act: -0.0000

Data Index: 34927 (C4 (Web Text))

Max Activating Token Index: 721

Text #3

Max Range: 0.4567. Min Range: -0.4567

Max Act: 0.3681. Min Act: -0.0000

Data Index: 1090546 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 0.4567. Min Range: -0.4567

Max Act: 0.3821. Min Act: -0.0000

Data Index: 723787 (C4 (Web Text))

Max Activating Token Index: 753

Text #5

Max Range: 0.4567. Min Range: -0.4567

Max Act: 0.3556. Min Act: -0.0000

Data Index: 194848 (C4 (Web Text))

Max Activating Token Index: 289

Text #6

Max Range: 0.4567. Min Range: -0.4567

Max Act: 0.3281. Min Act: -0.0000

Data Index: 876435 (C4 (Web Text))

Max Activating Token Index: 638

Text #7

Max Range: 0.4567. Min Range: -0.4567

Max Act: 0.3374. Min Act: -0.0000

Data Index: 633345 (C4 (Web Text))

Max Activating Token Index: 111

Text #8

Max Range: 0.4567. Min Range: -0.4567

Max Act: 0.3495. Min Act: -0.0000

Data Index: 46108 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 0.4567. Min Range: -0.4567

Max Act: 0.3197. Min Act: -0.0000

Data Index: 881389 (C4 (Web Text))

Max Activating Token Index: 610

Text #10

Max Range: 0.4567. Min Range: -0.4567

Max Act: 0.3222. Min Act: -0.0000

Data Index: 1014486 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 0.4567. Min Range: -0.4567

Max Act: 0.2763. Min Act: -0.0000

Data Index: 65108 (C4 (Web Text))

Max Activating Token Index: 614

Text #12

Max Range: 0.4567. Min Range: -0.4567

Max Act: 0.2980. Min Act: -0.0000

Data Index: 470598 (C4 (Web Text))

Max Activating Token Index: 572

Text #13

Max Range: 0.4567. Min Range: -0.4567

Max Act: 0.2884. Min Act: -0.0000

Data Index: 256160 (C4 (Web Text))

Max Activating Token Index: 67

Text #14

Max Range: 0.4567. Min Range: -0.4567

Max Act: 0.2806. Min Act: 0.0000

Data Index: 1134972 (C4 (Web Text))

Max Activating Token Index: 913

Text #15

Max Range: 0.4567. Min Range: -0.4567

Max Act: 0.2811. Min Act: -0.0000

Data Index: 1020167 (C4 (Web Text))

Max Activating Token Index: 332

Text #16

Max Range: 0.4567. Min Range: -0.4567

Max Act: 0.2806. Min Act: -0.0000

Data Index: 981257 (C4 (Web Text))

Max Activating Token Index: 618

Text #17

Max Range: 0.4567. Min Range: -0.4567

Max Act: 0.2985. Min Act: 0.0000

Data Index: 456939 (C4 (Web Text))

Max Activating Token Index: 853

Text #18

Max Range: 0.4567. Min Range: -0.4567

Max Act: 0.2880. Min Act: -0.0000

Data Index: 794783 (C4 (Web Text))

Max Activating Token Index: 597

Text #19

Max Range: 0.4567. Min Range: -0.4567

Max Act: 0.2843. Min Act: -0.0000

Data Index: 1041372 (C4 (Web Text))

Max Activating Token Index: 548