Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3192 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8807. Min Range: -0.8807

Max Act: 0.8807. Min Act: -0.0001

Data Index: 235069 (C4 (Web Text))

Max Activating Token Index: 603

Text #1

Max Range: 0.8807. Min Range: -0.8807

Max Act: 0.7258. Min Act: -0.0001

Data Index: 492746 (C4 (Web Text))

Max Activating Token Index: 880

Text #2

Max Range: 0.8807. Min Range: -0.8807

Max Act: 0.7010. Min Act: -0.0000

Data Index: 783058 (C4 (Web Text))

Max Activating Token Index: 844

Text #3

Max Range: 0.8807. Min Range: -0.8807

Max Act: 0.7153. Min Act: -0.0001

Data Index: 750656 (C4 (Web Text))

Max Activating Token Index: 197

Text #4

Max Range: 0.8807. Min Range: -0.8807

Max Act: 0.6645. Min Act: -0.0000

Data Index: 1024843 (C4 (Web Text))

Max Activating Token Index: 186

Text #5

Max Range: 0.8807. Min Range: -0.8807

Max Act: 0.6823. Min Act: -0.0001

Data Index: 1259780 (C4 (Web Text))

Max Activating Token Index: 468

Text #6

Max Range: 0.8807. Min Range: -0.8807

Max Act: 0.6699. Min Act: -0.0000

Data Index: 460064 (C4 (Web Text))

Max Activating Token Index: 554

Text #7

Max Range: 0.8807. Min Range: -0.8807

Max Act: 0.6070. Min Act: -0.0000

Data Index: 1202467 (C4 (Web Text))

Max Activating Token Index: 391

Text #8

Max Range: 0.8807. Min Range: -0.8807

Max Act: 0.6199. Min Act: -0.0000

Data Index: 419981 (C4 (Web Text))

Max Activating Token Index: 364

Text #9

Max Range: 0.8807. Min Range: -0.8807

Max Act: 0.6024. Min Act: -0.0000

Data Index: 1012163 (C4 (Web Text))

Max Activating Token Index: 844

Text #10

Max Range: 0.8807. Min Range: -0.8807

Max Act: 0.5915. Min Act: -0.0000

Data Index: 1135689 (C4 (Web Text))

Max Activating Token Index: 879

Text #11

Max Range: 0.8807. Min Range: -0.8807

Max Act: 0.6029. Min Act: -0.0001

Data Index: 110301 (C4 (Web Text))

Max Activating Token Index: 33

Text #12

Max Range: 0.8807. Min Range: -0.8807

Max Act: 0.5811. Min Act: 0.0002

Data Index: 685187 (C4 (Web Text))

Max Activating Token Index: 229

Text #13

Max Range: 0.8807. Min Range: -0.8807

Max Act: 0.5663. Min Act: -0.0000

Data Index: 496674 (C4 (Web Text))

Max Activating Token Index: 309

Text #14

Max Range: 0.8807. Min Range: -0.8807

Max Act: 0.5166. Min Act: -0.0000

Data Index: 641609 (C4 (Web Text))

Max Activating Token Index: 624

Text #15

Max Range: 0.8807. Min Range: -0.8807

Max Act: 0.5615. Min Act: 0.0003

Data Index: 719263 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 0.8807. Min Range: -0.8807

Max Act: 0.5574. Min Act: 0.0001

Data Index: 1114063 (C4 (Web Text))

Max Activating Token Index: 1002

Text #17

Max Range: 0.8807. Min Range: -0.8807

Max Act: 0.5874. Min Act: -0.0001

Data Index: 1104118 (C4 (Web Text))

Max Activating Token Index: 609

Text #18

Max Range: 0.8807. Min Range: -0.8807

Max Act: 0.5477. Min Act: -0.0001

Data Index: 1105077 (C4 (Web Text))

Max Activating Token Index: 791

Text #19

Max Range: 0.8807. Min Range: -0.8807

Max Act: 0.5443. Min Act: -0.0001

Data Index: 274419 (C4 (Web Text))

Max Activating Token Index: 479