Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2923 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.9795. Min Range: -0.9795

Max Act: 0.9795. Min Act: -0.0001

Data Index: 501026 (C4 (Web Text))

Max Activating Token Index: 834

Text #1

Max Range: 0.9795. Min Range: -0.9795

Max Act: 0.9328. Min Act: -0.0001

Data Index: 365881 (C4 (Web Text))

Max Activating Token Index: 155

Text #2

Max Range: 0.9795. Min Range: -0.9795

Max Act: 0.9520. Min Act: -0.0001

Data Index: 1050873 (C4 (Web Text))

Max Activating Token Index: 445

Text #3

Max Range: 0.9795. Min Range: -0.9795

Max Act: 0.8902. Min Act: -0.0001

Data Index: 922953 (C4 (Web Text))

Max Activating Token Index: 930

Text #4

Max Range: 0.9795. Min Range: -0.9795

Max Act: 0.8831. Min Act: -0.0001

Data Index: 265104 (C4 (Web Text))

Max Activating Token Index: 131

Text #5

Max Range: 0.9795. Min Range: -0.9795

Max Act: 0.8522. Min Act: -0.0001

Data Index: 250302 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 0.9795. Min Range: -0.9795

Max Act: 0.8238. Min Act: -0.0001

Data Index: 426648 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 0.9795. Min Range: -0.9795

Max Act: 0.8989. Min Act: -0.0001

Data Index: 192328 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 0.9795. Min Range: -0.9795

Max Act: 0.9159. Min Act: -0.0001

Data Index: 407814 (C4 (Web Text))

Max Activating Token Index: 68

Text #9

Max Range: 0.9795. Min Range: -0.9795

Max Act: 0.8631. Min Act: -0.0001

Data Index: 819209 (C4 (Web Text))

Max Activating Token Index: 36

Text #10

Max Range: 0.9795. Min Range: -0.9795

Max Act: 0.8963. Min Act: -0.0001

Data Index: 534127 (C4 (Web Text))

Max Activating Token Index: 667

Text #11

Max Range: 0.9795. Min Range: -0.9795

Max Act: 0.8222. Min Act: -0.0001

Data Index: 843331 (C4 (Web Text))

Max Activating Token Index: 490

Text #12

Max Range: 0.9795. Min Range: -0.9795

Max Act: 0.9355. Min Act: -0.0001

Data Index: 1004693 (C4 (Web Text))

Max Activating Token Index: 343

Text #13

Max Range: 0.9795. Min Range: -0.9795

Max Act: 0.8400. Min Act: -0.0001

Data Index: 128101 (C4 (Web Text))

Max Activating Token Index: 824

Text #14

Max Range: 0.9795. Min Range: -0.9795

Max Act: 0.8700. Min Act: -0.0001

Data Index: 147871 (C4 (Web Text))

Max Activating Token Index: 161

Text #15

Max Range: 0.9795. Min Range: -0.9795

Max Act: 0.8122. Min Act: -0.0001

Data Index: 1015055 (C4 (Web Text))

Max Activating Token Index: 943

Text #16

Max Range: 0.9795. Min Range: -0.9795

Max Act: 0.8057. Min Act: -0.0001

Data Index: 372006 (C4 (Web Text))

Max Activating Token Index: 666

Text #17

Max Range: 0.9795. Min Range: -0.9795

Max Act: 0.8411. Min Act: -0.0001

Data Index: 462870 (C4 (Web Text))

Max Activating Token Index: 972

Text #18

Max Range: 0.9795. Min Range: -0.9795

Max Act: 0.7937. Min Act: -0.0001

Data Index: 1084636 (C4 (Web Text))

Max Activating Token Index: 998

Text #19

Max Range: 0.9795. Min Range: -0.9795

Max Act: 0.8177. Min Act: -0.0001

Data Index: 836804 (C4 (Web Text))

Max Activating Token Index: 635