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

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

Neuron 1902 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9257. Min Range: -0.9257

Max Act: 0.9257. Min Act: -0.0000

Data Index: 495677 (C4 (Web Text))

Max Activating Token Index: 758

Text #1

Max Range: 0.9257. Min Range: -0.9257

Max Act: 0.7448. Min Act: -0.0000

Data Index: 450112 (C4 (Web Text))

Max Activating Token Index: 75

Text #2

Max Range: 0.9257. Min Range: -0.9257

Max Act: 0.6709. Min Act: -0.0000

Data Index: 1306609 (C4 (Web Text))

Max Activating Token Index: 774

Text #3

Max Range: 0.9257. Min Range: -0.9257

Max Act: 0.5738. Min Act: -0.0000

Data Index: 1208513 (C4 (Web Text))

Max Activating Token Index: 860

Text #4

Max Range: 0.9257. Min Range: -0.9257

Max Act: 0.7786. Min Act: -0.0000

Data Index: 193972 (C4 (Web Text))

Max Activating Token Index: 166

Text #5

Max Range: 0.9257. Min Range: -0.9257

Max Act: 0.5603. Min Act: -0.0000

Data Index: 1299884 (C4 (Web Text))

Max Activating Token Index: 41

Text #6

Max Range: 0.9257. Min Range: -0.9257

Max Act: 0.4647. Min Act: -0.0000

Data Index: 740232 (C4 (Web Text))

Max Activating Token Index: 627

Text #7

Max Range: 0.9257. Min Range: -0.9257

Max Act: 0.5379. Min Act: -0.0000

Data Index: 299011 (C4 (Web Text))

Max Activating Token Index: 52

Text #8

Max Range: 0.9257. Min Range: -0.9257

Max Act: 0.5664. Min Act: -0.0000

Data Index: 1014292 (C4 (Web Text))

Max Activating Token Index: 908

Text #9

Max Range: 0.9257. Min Range: -0.9257

Max Act: 0.5075. Min Act: -0.0000

Data Index: 1141817 (C4 (Web Text))

Max Activating Token Index: 388

Text #10

Max Range: 0.9257. Min Range: -0.9257

Max Act: 0.5243. Min Act: -0.0000

Data Index: 888534 (C4 (Web Text))

Max Activating Token Index: 383

Text #11

Max Range: 0.9257. Min Range: -0.9257

Max Act: 0.5270. Min Act: -0.0000

Data Index: 715915 (C4 (Web Text))

Max Activating Token Index: 10

Text #12

Max Range: 0.9257. Min Range: -0.9257

Max Act: 0.5383. Min Act: -0.0000

Data Index: 619073 (C4 (Web Text))

Max Activating Token Index: 764

Text #13

Max Range: 0.9257. Min Range: -0.9257

Max Act: 0.4960. Min Act: -0.0000

Data Index: 837836 (C4 (Web Text))

Max Activating Token Index: 999

Text #14

Max Range: 0.9257. Min Range: -0.9257

Max Act: 0.5594. Min Act: -0.0000

Data Index: 255785 (C4 (Web Text))

Max Activating Token Index: 687

Text #15

Max Range: 0.9257. Min Range: -0.9257

Max Act: 0.4909. Min Act: -0.0000

Data Index: 698211 (C4 (Web Text))

Max Activating Token Index: 594

Text #16

Max Range: 0.9257. Min Range: -0.9257

Max Act: 0.4951. Min Act: -0.0000

Data Index: 717771 (C4 (Web Text))

Max Activating Token Index: 346

Text #17

Max Range: 0.9257. Min Range: -0.9257

Max Act: 0.4509. Min Act: -0.0000

Data Index: 306196 (C4 (Web Text))

Max Activating Token Index: 561

Text #18

Max Range: 0.9257. Min Range: -0.9257

Max Act: 0.4639. Min Act: -0.0000

Data Index: 1203986 (C4 (Web Text))

Max Activating Token Index: 601

Text #19

Max Range: 0.9257. Min Range: -0.9257

Max Act: 0.4726. Min Act: -0.0000

Data Index: 1341351 (C4 (Web Text))

Max Activating Token Index: 65