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

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

Neuron 2130 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.6029. Min Act: -0.0001

Data Index: 507244 (C4 (Web Text))

Max Activating Token Index: 848

Text #1

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.2090. Min Act: -0.0001

Data Index: 255384 (C4 (Web Text))

Max Activating Token Index: 613

Text #2

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.3132. Min Act: -0.0001

Data Index: 235103 (C4 (Web Text))

Max Activating Token Index: 384

Text #3

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.2361. Min Act: -0.0001

Data Index: 1007448 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.2682. Min Act: -0.0001

Data Index: 445616 (C4 (Web Text))

Max Activating Token Index: 806

Text #5

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.3199. Min Act: -0.0001

Data Index: 159767 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.0671. Min Act: -0.0001

Data Index: 345145 (C4 (Web Text))

Max Activating Token Index: 148

Text #7

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.1362. Min Act: -0.0001

Data Index: 394328 (C4 (Web Text))

Max Activating Token Index: 699

Text #8

Max Range: 1.6029. Min Range: -1.6029

Max Act: 0.9956. Min Act: -0.0001

Data Index: 739361 (C4 (Web Text))

Max Activating Token Index: 714

Text #9

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.0440. Min Act: -0.0001

Data Index: 999071 (C4 (Web Text))

Max Activating Token Index: 374

Text #10

Max Range: 1.6029. Min Range: -1.6029

Max Act: 0.9804. Min Act: -0.0001

Data Index: 1091213 (C4 (Web Text))

Max Activating Token Index: 74

Text #11

Max Range: 1.6029. Min Range: -1.6029

Max Act: 0.9703. Min Act: -0.0001

Data Index: 375217 (C4 (Web Text))

Max Activating Token Index: 959

Text #12

Max Range: 1.6029. Min Range: -1.6029

Max Act: 0.8909. Min Act: -0.0001

Data Index: 1121994 (C4 (Web Text))

Max Activating Token Index: 61

Text #13

Max Range: 1.6029. Min Range: -1.6029

Max Act: 0.8943. Min Act: -0.0001

Data Index: 618139 (C4 (Web Text))

Max Activating Token Index: 1004

Text #14

Max Range: 1.6029. Min Range: -1.6029

Max Act: 0.9466. Min Act: -0.0001

Data Index: 200483 (C4 (Web Text))

Max Activating Token Index: 1015

Text #15

Max Range: 1.6029. Min Range: -1.6029

Max Act: 0.9402. Min Act: -0.0001

Data Index: 784751 (C4 (Web Text))

Max Activating Token Index: 563

Text #16

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.0504. Min Act: -0.0001

Data Index: 981803 (C4 (Web Text))

Max Activating Token Index: 679

Text #17

Max Range: 1.6029. Min Range: -1.6029

Max Act: 0.8098. Min Act: -0.0001

Data Index: 881034 (C4 (Web Text))

Max Activating Token Index: 749

Text #18

Max Range: 1.6029. Min Range: -1.6029

Max Act: 0.9239. Min Act: -0.0001

Data Index: 155768 (C4 (Web Text))

Max Activating Token Index: 661

Text #19

Max Range: 1.6029. Min Range: -1.6029

Max Act: 0.9139. Min Act: -0.0001

Data Index: 931700 (C4 (Web Text))

Max Activating Token Index: 488