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

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

Neuron 3227 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: 1.1983. Min Range: -1.1983

Max Act: 1.1983. Min Act: -0.0001

Data Index: 272779 (C4 (Web Text))

Max Activating Token Index: 102

Text #1

Max Range: 1.1983. Min Range: -1.1983

Max Act: 1.0364. Min Act: -0.0001

Data Index: 455109 (C4 (Web Text))

Max Activating Token Index: 547

Text #2

Max Range: 1.1983. Min Range: -1.1983

Max Act: 0.9683. Min Act: -0.0001

Data Index: 59119 (C4 (Web Text))

Max Activating Token Index: 756

Text #3

Max Range: 1.1983. Min Range: -1.1983

Max Act: 1.0215. Min Act: -0.0001

Data Index: 1230022 (C4 (Web Text))

Max Activating Token Index: 986

Text #4

Max Range: 1.1983. Min Range: -1.1983

Max Act: 0.9741. Min Act: -0.0001

Data Index: 1120908 (C4 (Web Text))

Max Activating Token Index: 157

Text #5

Max Range: 1.1983. Min Range: -1.1983

Max Act: 0.9123. Min Act: -0.0001

Data Index: 1032864 (C4 (Web Text))

Max Activating Token Index: 604

Text #6

Max Range: 1.1983. Min Range: -1.1983

Max Act: 0.8223. Min Act: -0.0001

Data Index: 1196302 (C4 (Web Text))

Max Activating Token Index: 844

Text #7

Max Range: 1.1983. Min Range: -1.1983

Max Act: 0.9258. Min Act: -0.0001

Data Index: 595299 (C4 (Web Text))

Max Activating Token Index: 223

Text #8

Max Range: 1.1983. Min Range: -1.1983

Max Act: 0.9204. Min Act: -0.0001

Data Index: 858414 (C4 (Web Text))

Max Activating Token Index: 517

Text #9

Max Range: 1.1983. Min Range: -1.1983

Max Act: 0.9107. Min Act: -0.0001

Data Index: 64132 (C4 (Web Text))

Max Activating Token Index: 219

Text #10

Max Range: 1.1983. Min Range: -1.1983

Max Act: 0.9103. Min Act: -0.0001

Data Index: 1320768 (C4 (Web Text))

Max Activating Token Index: 461

Text #11

Max Range: 1.1983. Min Range: -1.1983

Max Act: 0.8623. Min Act: -0.0001

Data Index: 892137 (C4 (Web Text))

Max Activating Token Index: 723

Text #12

Max Range: 1.1983. Min Range: -1.1983

Max Act: 0.9022. Min Act: -0.0001

Data Index: 489818 (C4 (Web Text))

Max Activating Token Index: 41

Text #13

Max Range: 1.1983. Min Range: -1.1983

Max Act: 0.7739. Min Act: -0.0001

Data Index: 167786 (C4 (Web Text))

Max Activating Token Index: 744

Text #14

Max Range: 1.1983. Min Range: -1.1983

Max Act: 0.8944. Min Act: -0.0001

Data Index: 1224105 (C4 (Web Text))

Max Activating Token Index: 938

Text #15

Max Range: 1.1983. Min Range: -1.1983

Max Act: 0.8601. Min Act: -0.0001

Data Index: 1288277 (C4 (Web Text))

Max Activating Token Index: 62

Text #16

Max Range: 1.1983. Min Range: -1.1983

Max Act: 0.8630. Min Act: -0.0001

Data Index: 833611 (C4 (Web Text))

Max Activating Token Index: 82

Text #17

Max Range: 1.1983. Min Range: -1.1983

Max Act: 0.8631. Min Act: -0.0001

Data Index: 1147241 (C4 (Web Text))

Max Activating Token Index: 864

Text #18

Max Range: 1.1983. Min Range: -1.1983

Max Act: 0.8573. Min Act: -0.0001

Data Index: 209636 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 1.1983. Min Range: -1.1983

Max Act: 0.8349. Min Act: -0.0001

Data Index: 1030362 (C4 (Web Text))

Max Activating Token Index: 25