Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 677 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.1089. Min Act: -0.0003

Data Index: 1273361 (C4 (Web Text))

Max Activating Token Index: 143

Text #1

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.1056. Min Act: -0.0003

Data Index: 1260943 (C4 (Web Text))

Max Activating Token Index: 420

Text #2

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0975. Min Act: -0.0003

Data Index: 1238411 (C4 (Web Text))

Max Activating Token Index: 742

Text #3

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0930. Min Act: -0.0003

Data Index: 840552 (C4 (Web Text))

Max Activating Token Index: 535

Text #4

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0911. Min Act: -0.0003

Data Index: 1277358 (C4 (Web Text))

Max Activating Token Index: 626

Text #5

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0952. Min Act: -0.0003

Data Index: 314135 (C4 (Web Text))

Max Activating Token Index: 171

Text #6

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0879. Min Act: -0.0003

Data Index: 314167 (C4 (Web Text))

Max Activating Token Index: 485

Text #7

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0923. Min Act: -0.0003

Data Index: 1105029 (C4 (Web Text))

Max Activating Token Index: 282

Text #8

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0907. Min Act: -0.0003

Data Index: 227905 (C4 (Web Text))

Max Activating Token Index: 407

Text #9

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0914. Min Act: -0.0003

Data Index: 968126 (C4 (Web Text))

Max Activating Token Index: 880

Text #10

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0884. Min Act: -0.0003

Data Index: 381619 (C4 (Web Text))

Max Activating Token Index: 918

Text #11

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0867. Min Act: -0.0004

Data Index: 988805 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0902. Min Act: -0.0003

Data Index: 489456 (C4 (Web Text))

Max Activating Token Index: 964

Text #13

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0889. Min Act: -0.0003

Data Index: 398676 (C4 (Web Text))

Max Activating Token Index: 147

Text #14

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0893. Min Act: -0.0003

Data Index: 964353 (C4 (Web Text))

Max Activating Token Index: 96

Text #15

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0882. Min Act: -0.0003

Data Index: 1258758 (C4 (Web Text))

Max Activating Token Index: 85

Text #16

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0882. Min Act: -0.0003

Data Index: 1100720 (C4 (Web Text))

Max Activating Token Index: 131

Text #17

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0869. Min Act: -0.0003

Data Index: 745409 (C4 (Web Text))

Max Activating Token Index: 203

Text #18

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0868. Min Act: -0.0003

Data Index: 690082 (C4 (Web Text))

Max Activating Token Index: 864

Text #19

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0854. Min Act: -0.0004

Data Index: 349507 (C4 (Web Text))

Max Activating Token Index: 747