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

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

Neuron 5081 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: 0.3368. Min Range: -0.3368

Max Act: 0.3368. Min Act: -0.0001

Data Index: 711154 (C4 (Web Text))

Max Activating Token Index: 861

Text #1

Max Range: 0.3368. Min Range: -0.3368

Max Act: 0.2692. Min Act: -0.0001

Data Index: 702159 (C4 (Web Text))

Max Activating Token Index: 627

Text #2

Max Range: 0.3368. Min Range: -0.3368

Max Act: 0.2647. Min Act: -0.0000

Data Index: 1064984 (C4 (Web Text))

Max Activating Token Index: 997

Text #3

Max Range: 0.3368. Min Range: -0.3368

Max Act: 0.2231. Min Act: -0.0001

Data Index: 454577 (C4 (Web Text))

Max Activating Token Index: 785

Text #4

Max Range: 0.3368. Min Range: -0.3368

Max Act: 0.2509. Min Act: -0.0000

Data Index: 634031 (C4 (Web Text))

Max Activating Token Index: 587

Text #5

Max Range: 0.3368. Min Range: -0.3368

Max Act: 0.2448. Min Act: -0.0001

Data Index: 823982 (C4 (Web Text))

Max Activating Token Index: 943

Text #6

Max Range: 0.3368. Min Range: -0.3368

Max Act: 0.2391. Min Act: -0.0001

Data Index: 62750 (C4 (Web Text))

Max Activating Token Index: 42

Text #7

Max Range: 0.3368. Min Range: -0.3368

Max Act: 0.2350. Min Act: -0.0000

Data Index: 827616 (C4 (Web Text))

Max Activating Token Index: 169

Text #8

Max Range: 0.3368. Min Range: -0.3368

Max Act: 0.2347. Min Act: -0.0001

Data Index: 384742 (C4 (Web Text))

Max Activating Token Index: 124

Text #9

Max Range: 0.3368. Min Range: -0.3368

Max Act: 0.2314. Min Act: -0.0000

Data Index: 555850 (C4 (Web Text))

Max Activating Token Index: 459

Text #10

Max Range: 0.3368. Min Range: -0.3368

Max Act: 0.2097. Min Act: -0.0000

Data Index: 831328 (C4 (Web Text))

Max Activating Token Index: 825

Text #11

Max Range: 0.3368. Min Range: -0.3368

Max Act: 0.2200. Min Act: -0.0000

Data Index: 1061651 (C4 (Web Text))

Max Activating Token Index: 834

Text #12

Max Range: 0.3368. Min Range: -0.3368

Max Act: 0.2066. Min Act: -0.0000

Data Index: 779223 (C4 (Web Text))

Max Activating Token Index: 686

Text #13

Max Range: 0.3368. Min Range: -0.3368

Max Act: 0.2195. Min Act: -0.0001

Data Index: 93446 (C4 (Web Text))

Max Activating Token Index: 636

Text #14

Max Range: 0.3368. Min Range: -0.3368

Max Act: 0.2021. Min Act: -0.0001

Data Index: 504479 (C4 (Web Text))

Max Activating Token Index: 985

Text #15

Max Range: 0.3368. Min Range: -0.3368

Max Act: 0.2063. Min Act: -0.0000

Data Index: 842381 (C4 (Web Text))

Max Activating Token Index: 957

Text #16

Max Range: 0.3368. Min Range: -0.3368

Max Act: 0.2317. Min Act: -0.0000

Data Index: 459939 (C4 (Web Text))

Max Activating Token Index: 372

Text #17

Max Range: 0.3368. Min Range: -0.3368

Max Act: 0.2110. Min Act: -0.0001

Data Index: 967309 (C4 (Web Text))

Max Activating Token Index: 882

Text #18

Max Range: 0.3368. Min Range: -0.3368

Max Act: 0.2112. Min Act: -0.0001

Data Index: 781279 (C4 (Web Text))

Max Activating Token Index: 837

Text #19

Max Range: 0.3368. Min Range: -0.3368

Max Act: 0.2033. Min Act: -0.0000

Data Index: 880836 (C4 (Web Text))

Max Activating Token Index: 1018