Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3323 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.8736. Min Range: -1.8736

Max Act: 1.8736. Min Act: -0.0001

Data Index: 464156 (C4 (Web Text))

Max Activating Token Index: 744

Text #1

Max Range: 1.8736. Min Range: -1.8736

Max Act: 1.4939. Min Act: -0.0001

Data Index: 1183959 (C4 (Web Text))

Max Activating Token Index: 132

Text #2

Max Range: 1.8736. Min Range: -1.8736

Max Act: 1.3963. Min Act: -0.0001

Data Index: 1110447 (C4 (Web Text))

Max Activating Token Index: 62

Text #3

Max Range: 1.8736. Min Range: -1.8736

Max Act: 1.3668. Min Act: -0.0001

Data Index: 756177 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 1.8736. Min Range: -1.8736

Max Act: 1.2611. Min Act: -0.0001

Data Index: 555701 (C4 (Web Text))

Max Activating Token Index: 36

Text #5

Max Range: 1.8736. Min Range: -1.8736

Max Act: 1.3275. Min Act: -0.0001

Data Index: 353413 (C4 (Web Text))

Max Activating Token Index: 269

Text #6

Max Range: 1.8736. Min Range: -1.8736

Max Act: 1.2424. Min Act: -0.0001

Data Index: 1294217 (C4 (Web Text))

Max Activating Token Index: 448

Text #7

Max Range: 1.8736. Min Range: -1.8736

Max Act: 1.1659. Min Act: -0.0001

Data Index: 1237346 (C4 (Web Text))

Max Activating Token Index: 423

Text #8

Max Range: 1.8736. Min Range: -1.8736

Max Act: 1.1751. Min Act: -0.0001

Data Index: 1339361 (C4 (Web Text))

Max Activating Token Index: 49

Text #9

Max Range: 1.8736. Min Range: -1.8736

Max Act: 1.0516. Min Act: -0.0001

Data Index: 1351211 (C4 (Web Text))

Max Activating Token Index: 575

Text #10

Max Range: 1.8736. Min Range: -1.8736

Max Act: 1.1568. Min Act: -0.0001

Data Index: 818898 (C4 (Web Text))

Max Activating Token Index: 540

Text #11

Max Range: 1.8736. Min Range: -1.8736

Max Act: 1.1129. Min Act: -0.0001

Data Index: 442450 (C4 (Web Text))

Max Activating Token Index: 902

Text #12

Max Range: 1.8736. Min Range: -1.8736

Max Act: 1.1313. Min Act: -0.0001

Data Index: 383210 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 1.8736. Min Range: -1.8736

Max Act: 1.0557. Min Act: -0.0001

Data Index: 1624312 (Python Code)

Max Activating Token Index: 168

Text #14

Max Range: 1.8736. Min Range: -1.8736

Max Act: 1.1109. Min Act: -0.0001

Data Index: 605942 (C4 (Web Text))

Max Activating Token Index: 872

Text #15

Max Range: 1.8736. Min Range: -1.8736

Max Act: 1.0599. Min Act: -0.0001

Data Index: 540420 (C4 (Web Text))

Max Activating Token Index: 956

Text #16

Max Range: 1.8736. Min Range: -1.8736

Max Act: 1.1014. Min Act: -0.0001

Data Index: 1114260 (C4 (Web Text))

Max Activating Token Index: 744

Text #17

Max Range: 1.8736. Min Range: -1.8736

Max Act: 1.0492. Min Act: -0.0001

Data Index: 549952 (C4 (Web Text))

Max Activating Token Index: 79

Text #18

Max Range: 1.8736. Min Range: -1.8736

Max Act: 0.9666. Min Act: -0.0001

Data Index: 230782 (C4 (Web Text))

Max Activating Token Index: 550

Text #19

Max Range: 1.8736. Min Range: -1.8736

Max Act: 1.0810. Min Act: -0.0001

Data Index: 328234 (C4 (Web Text))

Max Activating Token Index: 38