Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1622 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9592. Min Range: -0.9592

Max Act: 0.9592. Min Act: -0.0001

Data Index: 209608 (C4 (Web Text))

Max Activating Token Index: 652

Text #1

Max Range: 0.9592. Min Range: -0.9592

Max Act: 0.8581. Min Act: -0.0001

Data Index: 179897 (C4 (Web Text))

Max Activating Token Index: 278

Text #2

Max Range: 0.9592. Min Range: -0.9592

Max Act: 0.9494. Min Act: -0.0001

Data Index: 554411 (C4 (Web Text))

Max Activating Token Index: 760

Text #3

Max Range: 0.9592. Min Range: -0.9592

Max Act: 0.8955. Min Act: -0.0001

Data Index: 1055179 (C4 (Web Text))

Max Activating Token Index: 778

Text #4

Max Range: 0.9592. Min Range: -0.9592

Max Act: 0.8752. Min Act: -0.0001

Data Index: 1342697 (C4 (Web Text))

Max Activating Token Index: 899

Text #5

Max Range: 0.9592. Min Range: -0.9592

Max Act: 0.9368. Min Act: -0.0001

Data Index: 361372 (C4 (Web Text))

Max Activating Token Index: 934

Text #6

Max Range: 0.9592. Min Range: -0.9592

Max Act: 0.8672. Min Act: -0.0001

Data Index: 881766 (C4 (Web Text))

Max Activating Token Index: 751

Text #7

Max Range: 0.9592. Min Range: -0.9592

Max Act: 0.8201. Min Act: -0.0001

Data Index: 793023 (C4 (Web Text))

Max Activating Token Index: 859

Text #8

Max Range: 0.9592. Min Range: -0.9592

Max Act: 0.8415. Min Act: -0.0001

Data Index: 916156 (C4 (Web Text))

Max Activating Token Index: 698

Text #9

Max Range: 0.9592. Min Range: -0.9592

Max Act: 0.8022. Min Act: -0.0001

Data Index: 1180422 (C4 (Web Text))

Max Activating Token Index: 740

Text #10

Max Range: 0.9592. Min Range: -0.9592

Max Act: 0.8464. Min Act: -0.0001

Data Index: 325863 (C4 (Web Text))

Max Activating Token Index: 695

Text #11

Max Range: 0.9592. Min Range: -0.9592

Max Act: 0.8533. Min Act: -0.0001

Data Index: 2692 (C4 (Web Text))

Max Activating Token Index: 234

Text #12

Max Range: 0.9592. Min Range: -0.9592

Max Act: 0.8491. Min Act: -0.0001

Data Index: 672002 (C4 (Web Text))

Max Activating Token Index: 841

Text #13

Max Range: 0.9592. Min Range: -0.9592

Max Act: 0.8494. Min Act: -0.0001

Data Index: 478490 (C4 (Web Text))

Max Activating Token Index: 956

Text #14

Max Range: 0.9592. Min Range: -0.9592

Max Act: 0.7663. Min Act: -0.0001

Data Index: 633364 (C4 (Web Text))

Max Activating Token Index: 590

Text #15

Max Range: 0.9592. Min Range: -0.9592

Max Act: 0.7878. Min Act: -0.0001

Data Index: 906397 (C4 (Web Text))

Max Activating Token Index: 867

Text #16

Max Range: 0.9592. Min Range: -0.9592

Max Act: 0.8257. Min Act: -0.0001

Data Index: 3845 (C4 (Web Text))

Max Activating Token Index: 935

Text #17

Max Range: 0.9592. Min Range: -0.9592

Max Act: 0.7129. Min Act: -0.0001

Data Index: 627861 (C4 (Web Text))

Max Activating Token Index: 765

Text #18

Max Range: 0.9592. Min Range: -0.9592

Max Act: 0.7976. Min Act: -0.0001

Data Index: 208031 (C4 (Web Text))

Max Activating Token Index: 958

Text #19

Max Range: 0.9592. Min Range: -0.9592

Max Act: 0.8712. Min Act: -0.0001

Data Index: 887759 (C4 (Web Text))

Max Activating Token Index: 774