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

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

Neuron 3739 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1368. Min Range: -1.1368

Max Act: 1.1368. Min Act: -0.0001

Data Index: 349426 (C4 (Web Text))

Max Activating Token Index: 496

Text #1

Max Range: 1.1368. Min Range: -1.1368

Max Act: 1.1005. Min Act: -0.0001

Data Index: 451407 (C4 (Web Text))

Max Activating Token Index: 727

Text #2

Max Range: 1.1368. Min Range: -1.1368

Max Act: 1.0381. Min Act: -0.0001

Data Index: 931938 (C4 (Web Text))

Max Activating Token Index: 562

Text #3

Max Range: 1.1368. Min Range: -1.1368

Max Act: 1.0348. Min Act: -0.0001

Data Index: 221731 (C4 (Web Text))

Max Activating Token Index: 560

Text #4

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.9430. Min Act: -0.0001

Data Index: 37467 (C4 (Web Text))

Max Activating Token Index: 718

Text #5

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.9075. Min Act: -0.0001

Data Index: 959419 (C4 (Web Text))

Max Activating Token Index: 95

Text #6

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.9418. Min Act: -0.0001

Data Index: 355698 (C4 (Web Text))

Max Activating Token Index: 700

Text #7

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.8584. Min Act: -0.0001

Data Index: 414855 (C4 (Web Text))

Max Activating Token Index: 572

Text #8

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.7095. Min Act: -0.0001

Data Index: 799260 (C4 (Web Text))

Max Activating Token Index: 214

Text #9

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.6215. Min Act: -0.0001

Data Index: 1224197 (C4 (Web Text))

Max Activating Token Index: 783

Text #10

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.7738. Min Act: -0.0001

Data Index: 422502 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.7716. Min Act: -0.0001

Data Index: 205192 (C4 (Web Text))

Max Activating Token Index: 638

Text #12

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.7589. Min Act: -0.0001

Data Index: 891808 (C4 (Web Text))

Max Activating Token Index: 492

Text #13

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.8080. Min Act: -0.0001

Data Index: 882508 (C4 (Web Text))

Max Activating Token Index: 607

Text #14

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.7043. Min Act: -0.0001

Data Index: 611256 (C4 (Web Text))

Max Activating Token Index: 879

Text #15

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.7088. Min Act: -0.0001

Data Index: 786763 (C4 (Web Text))

Max Activating Token Index: 514

Text #16

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.7257. Min Act: -0.0001

Data Index: 1175539 (C4 (Web Text))

Max Activating Token Index: 757

Text #17

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.7900. Min Act: -0.0001

Data Index: 37139 (C4 (Web Text))

Max Activating Token Index: 621

Text #18

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.6743. Min Act: -0.0001

Data Index: 1110300 (C4 (Web Text))

Max Activating Token Index: 623

Text #19

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.7249. Min Act: -0.0001

Data Index: 355855 (C4 (Web Text))

Max Activating Token Index: 172