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

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

Neuron 5744 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.3580. Min Act: -0.0000

Data Index: 398594 (C4 (Web Text))

Max Activating Token Index: 998

Text #1

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.3393. Min Act: -0.0001

Data Index: 326133 (C4 (Web Text))

Max Activating Token Index: 631

Text #2

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.3346. Min Act: -0.0000

Data Index: 219136 (C4 (Web Text))

Max Activating Token Index: 695

Text #3

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.3281. Min Act: -0.0000

Data Index: 618371 (C4 (Web Text))

Max Activating Token Index: 759

Text #4

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.3472. Min Act: -0.0000

Data Index: 987368 (C4 (Web Text))

Max Activating Token Index: 847

Text #5

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.3086. Min Act: -0.0000

Data Index: 432804 (C4 (Web Text))

Max Activating Token Index: 680

Text #6

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2990. Min Act: -0.0000

Data Index: 774818 (C4 (Web Text))

Max Activating Token Index: 463

Text #7

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.3205. Min Act: -0.0000

Data Index: 1201529 (C4 (Web Text))

Max Activating Token Index: 899

Text #8

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.3067. Min Act: -0.0000

Data Index: 876771 (C4 (Web Text))

Max Activating Token Index: 209

Text #9

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.3075. Min Act: -0.0000

Data Index: 1119167 (C4 (Web Text))

Max Activating Token Index: 67

Text #10

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2845. Min Act: -0.0000

Data Index: 770310 (C4 (Web Text))

Max Activating Token Index: 871

Text #11

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2750. Min Act: -0.0001

Data Index: 938578 (C4 (Web Text))

Max Activating Token Index: 845

Text #12

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2857. Min Act: -0.0000

Data Index: 400923 (C4 (Web Text))

Max Activating Token Index: 545

Text #13

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2858. Min Act: -0.0000

Data Index: 128774 (C4 (Web Text))

Max Activating Token Index: 742

Text #14

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2834. Min Act: -0.0000

Data Index: 917485 (C4 (Web Text))

Max Activating Token Index: 615

Text #15

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2963. Min Act: -0.0000

Data Index: 847161 (C4 (Web Text))

Max Activating Token Index: 712

Text #16

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2817. Min Act: -0.0000

Data Index: 874598 (C4 (Web Text))

Max Activating Token Index: 660

Text #17

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2729. Min Act: -0.0000

Data Index: 345558 (C4 (Web Text))

Max Activating Token Index: 383

Text #18

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2863. Min Act: -0.0000

Data Index: 918377 (C4 (Web Text))

Max Activating Token Index: 158

Text #19

Max Range: 0.3580. Min Range: -0.3580

Max Act: 0.2762. Min Act: -0.0000

Data Index: 822450 (C4 (Web Text))

Max Activating Token Index: 771