Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2707 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6208. Min Range: -0.6208

Max Act: 0.5942. Min Act: -0.0002

Data Index: 1159934 (C4 (Web Text))

Max Activating Token Index: 666

Text #1

Max Range: 0.6208. Min Range: -0.6208

Max Act: 0.6208. Min Act: -0.0002

Data Index: 988019 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 0.6208. Min Range: -0.6208

Max Act: 0.5723. Min Act: -0.0002

Data Index: 215523 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 0.6208. Min Range: -0.6208

Max Act: 0.5029. Min Act: -0.0002

Data Index: 376950 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 0.6208. Min Range: -0.6208

Max Act: 0.4735. Min Act: -0.0002

Data Index: 160753 (C4 (Web Text))

Max Activating Token Index: 726

Text #5

Max Range: 0.6208. Min Range: -0.6208

Max Act: 0.4653. Min Act: -0.0002

Data Index: 1113607 (C4 (Web Text))

Max Activating Token Index: 407

Text #6

Max Range: 0.6208. Min Range: -0.6208

Max Act: 0.4831. Min Act: -0.0002

Data Index: 919885 (C4 (Web Text))

Max Activating Token Index: 303

Text #7

Max Range: 0.6208. Min Range: -0.6208

Max Act: 0.4475. Min Act: -0.0002

Data Index: 1215296 (C4 (Web Text))

Max Activating Token Index: 137

Text #8

Max Range: 0.6208. Min Range: -0.6208

Max Act: 0.4591. Min Act: -0.0002

Data Index: 895102 (C4 (Web Text))

Max Activating Token Index: 731

Text #9

Max Range: 0.6208. Min Range: -0.6208

Max Act: 0.4410. Min Act: -0.0002

Data Index: 1098822 (C4 (Web Text))

Max Activating Token Index: 873

Text #10

Max Range: 0.6208. Min Range: -0.6208

Max Act: 0.4222. Min Act: -0.0002

Data Index: 32022 (C4 (Web Text))

Max Activating Token Index: 7

Text #11

Max Range: 0.6208. Min Range: -0.6208

Max Act: 0.4118. Min Act: -0.0002

Data Index: 264193 (C4 (Web Text))

Max Activating Token Index: 485

Text #12

Max Range: 0.6208. Min Range: -0.6208

Max Act: 0.4305. Min Act: -0.0002

Data Index: 74870 (C4 (Web Text))

Max Activating Token Index: 690

Text #13

Max Range: 0.6208. Min Range: -0.6208

Max Act: 0.4559. Min Act: -0.0002

Data Index: 688149 (C4 (Web Text))

Max Activating Token Index: 738

Text #14

Max Range: 0.6208. Min Range: -0.6208

Max Act: 0.4044. Min Act: -0.0002

Data Index: 756713 (C4 (Web Text))

Max Activating Token Index: 880

Text #15

Max Range: 0.6208. Min Range: -0.6208

Max Act: 0.4283. Min Act: -0.0002

Data Index: 35961 (C4 (Web Text))

Max Activating Token Index: 804

Text #16

Max Range: 0.6208. Min Range: -0.6208

Max Act: 0.4248. Min Act: -0.0002

Data Index: 669111 (C4 (Web Text))

Max Activating Token Index: 898

Text #17

Max Range: 0.6208. Min Range: -0.6208

Max Act: 0.3828. Min Act: -0.0002

Data Index: 1210422 (C4 (Web Text))

Max Activating Token Index: 113

Text #18

Max Range: 0.6208. Min Range: -0.6208

Max Act: 0.4013. Min Act: -0.0002

Data Index: 78318 (C4 (Web Text))

Max Activating Token Index: 439

Text #19

Max Range: 0.6208. Min Range: -0.6208

Max Act: 0.3476. Min Act: -0.0002

Data Index: 1251468 (C4 (Web Text))

Max Activating Token Index: 771