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

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

Neuron 1865 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: 1.5641. Min Range: -1.5641

Max Act: 1.5588. Min Act: -0.0001

Data Index: 1280353 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 1.5641. Min Range: -1.5641

Max Act: 1.5641. Min Act: -0.0001

Data Index: 1020934 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 1.5641. Min Range: -1.5641

Max Act: 1.5182. Min Act: -0.0001

Data Index: 934365 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 1.5641. Min Range: -1.5641

Max Act: 1.4869. Min Act: -0.0001

Data Index: 448003 (C4 (Web Text))

Max Activating Token Index: 616

Text #4

Max Range: 1.5641. Min Range: -1.5641

Max Act: 1.3758. Min Act: -0.0001

Data Index: 1138762 (C4 (Web Text))

Max Activating Token Index: 32

Text #5

Max Range: 1.5641. Min Range: -1.5641

Max Act: 1.2642. Min Act: -0.0001

Data Index: 421514 (C4 (Web Text))

Max Activating Token Index: 583

Text #6

Max Range: 1.5641. Min Range: -1.5641

Max Act: 1.3279. Min Act: -0.0001

Data Index: 1002269 (C4 (Web Text))

Max Activating Token Index: 505

Text #7

Max Range: 1.5641. Min Range: -1.5641

Max Act: 1.3595. Min Act: -0.0001

Data Index: 147615 (C4 (Web Text))

Max Activating Token Index: 988

Text #8

Max Range: 1.5641. Min Range: -1.5641

Max Act: 1.2896. Min Act: -0.0001

Data Index: 136426 (C4 (Web Text))

Max Activating Token Index: 182

Text #9

Max Range: 1.5641. Min Range: -1.5641

Max Act: 1.2054. Min Act: -0.0001

Data Index: 557874 (C4 (Web Text))

Max Activating Token Index: 702

Text #10

Max Range: 1.5641. Min Range: -1.5641

Max Act: 1.3129. Min Act: -0.0001

Data Index: 1174376 (C4 (Web Text))

Max Activating Token Index: 552

Text #11

Max Range: 1.5641. Min Range: -1.5641

Max Act: 1.2654. Min Act: -0.0001

Data Index: 680782 (C4 (Web Text))

Max Activating Token Index: 10

Text #12

Max Range: 1.5641. Min Range: -1.5641

Max Act: 1.3293. Min Act: -0.0001

Data Index: 1349310 (C4 (Web Text))

Max Activating Token Index: 386

Text #13

Max Range: 1.5641. Min Range: -1.5641

Max Act: 1.2680. Min Act: -0.0001

Data Index: 414792 (C4 (Web Text))

Max Activating Token Index: 423

Text #14

Max Range: 1.5641. Min Range: -1.5641

Max Act: 1.2424. Min Act: -0.0001

Data Index: 484936 (C4 (Web Text))

Max Activating Token Index: 502

Text #15

Max Range: 1.5641. Min Range: -1.5641

Max Act: 1.3436. Min Act: -0.0001

Data Index: 768238 (C4 (Web Text))

Max Activating Token Index: 503

Text #16

Max Range: 1.5641. Min Range: -1.5641

Max Act: 1.3435. Min Act: -0.0001

Data Index: 593725 (C4 (Web Text))

Max Activating Token Index: 274

Text #17

Max Range: 1.5641. Min Range: -1.5641

Max Act: 1.1410. Min Act: -0.0001

Data Index: 832572 (C4 (Web Text))

Max Activating Token Index: 179

Text #18

Max Range: 1.5641. Min Range: -1.5641

Max Act: 1.2996. Min Act: -0.0001

Data Index: 1197213 (C4 (Web Text))

Max Activating Token Index: 981

Text #19

Max Range: 1.5641. Min Range: -1.5641

Max Act: 1.2636. Min Act: -0.0001

Data Index: 113450 (C4 (Web Text))

Max Activating Token Index: 15