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

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

Neuron 2340 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: 0.3465. Min Range: -0.3465

Max Act: 0.3465. Min Act: -0.0001

Data Index: 641798 (C4 (Web Text))

Max Activating Token Index: 237

Text #1

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.3424. Min Act: -0.0001

Data Index: 770766 (C4 (Web Text))

Max Activating Token Index: 1001

Text #2

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.3330. Min Act: -0.0001

Data Index: 738871 (C4 (Web Text))

Max Activating Token Index: 991

Text #3

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.3114. Min Act: -0.0001

Data Index: 903974 (C4 (Web Text))

Max Activating Token Index: 218

Text #4

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.3115. Min Act: -0.0001

Data Index: 64350 (C4 (Web Text))

Max Activating Token Index: 288

Text #5

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.3014. Min Act: -0.0001

Data Index: 1089866 (C4 (Web Text))

Max Activating Token Index: 801

Text #6

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.3019. Min Act: -0.0001

Data Index: 468566 (C4 (Web Text))

Max Activating Token Index: 230

Text #7

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.2944. Min Act: -0.0001

Data Index: 880970 (C4 (Web Text))

Max Activating Token Index: 441

Text #8

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.2974. Min Act: -0.0001

Data Index: 1066805 (C4 (Web Text))

Max Activating Token Index: 329

Text #9

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.2911. Min Act: -0.0001

Data Index: 572269 (C4 (Web Text))

Max Activating Token Index: 649

Text #10

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.3018. Min Act: -0.0001

Data Index: 1278497 (C4 (Web Text))

Max Activating Token Index: 910

Text #11

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.3021. Min Act: -0.0001

Data Index: 268083 (C4 (Web Text))

Max Activating Token Index: 765

Text #12

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.2848. Min Act: -0.0001

Data Index: 882157 (C4 (Web Text))

Max Activating Token Index: 689

Text #13

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.2907. Min Act: -0.0001

Data Index: 1069786 (C4 (Web Text))

Max Activating Token Index: 171

Text #14

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.2708. Min Act: -0.0001

Data Index: 72947 (C4 (Web Text))

Max Activating Token Index: 202

Text #15

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.2823. Min Act: -0.0001

Data Index: 1238520 (C4 (Web Text))

Max Activating Token Index: 206

Text #16

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.2789. Min Act: -0.0001

Data Index: 1126506 (C4 (Web Text))

Max Activating Token Index: 64

Text #17

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.2720. Min Act: -0.0001

Data Index: 962468 (C4 (Web Text))

Max Activating Token Index: 438

Text #18

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.2684. Min Act: -0.0001

Data Index: 826451 (C4 (Web Text))

Max Activating Token Index: 902

Text #19

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.2734. Min Act: -0.0001

Data Index: 1055956 (C4 (Web Text))

Max Activating Token Index: 2