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

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

Neuron 2085 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5168. Min Range: -0.5168

Max Act: 0.5168. Min Act: -0.0003

Data Index: 1348452 (C4 (Web Text))

Max Activating Token Index: 907

Text #1

Max Range: 0.5168. Min Range: -0.5168

Max Act: 0.5160. Min Act: -0.0003

Data Index: 277792 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 0.5168. Min Range: -0.5168

Max Act: 0.4754. Min Act: -0.0003

Data Index: 284851 (C4 (Web Text))

Max Activating Token Index: 339

Text #3

Max Range: 0.5168. Min Range: -0.5168

Max Act: 0.5052. Min Act: -0.0003

Data Index: 359107 (C4 (Web Text))

Max Activating Token Index: 173

Text #4

Max Range: 0.5168. Min Range: -0.5168

Max Act: 0.4807. Min Act: -0.0003

Data Index: 1310154 (C4 (Web Text))

Max Activating Token Index: 577

Text #5

Max Range: 0.5168. Min Range: -0.5168

Max Act: 0.5005. Min Act: -0.0003

Data Index: 634433 (C4 (Web Text))

Max Activating Token Index: 387

Text #6

Max Range: 0.5168. Min Range: -0.5168

Max Act: 0.4812. Min Act: -0.0003

Data Index: 2261 (C4 (Web Text))

Max Activating Token Index: 462

Text #7

Max Range: 0.5168. Min Range: -0.5168

Max Act: 0.4766. Min Act: -0.0003

Data Index: 890551 (C4 (Web Text))

Max Activating Token Index: 528

Text #8

Max Range: 0.5168. Min Range: -0.5168

Max Act: 0.4629. Min Act: -0.0003

Data Index: 1306156 (C4 (Web Text))

Max Activating Token Index: 54

Text #9

Max Range: 0.5168. Min Range: -0.5168

Max Act: 0.4948. Min Act: -0.0003

Data Index: 709648 (C4 (Web Text))

Max Activating Token Index: 185

Text #10

Max Range: 0.5168. Min Range: -0.5168

Max Act: 0.4937. Min Act: -0.0003

Data Index: 810202 (C4 (Web Text))

Max Activating Token Index: 108

Text #11

Max Range: 0.5168. Min Range: -0.5168

Max Act: 0.4731. Min Act: -0.0003

Data Index: 8806 (C4 (Web Text))

Max Activating Token Index: 442

Text #12

Max Range: 0.5168. Min Range: -0.5168

Max Act: 0.5067. Min Act: -0.0003

Data Index: 1061318 (C4 (Web Text))

Max Activating Token Index: 200

Text #13

Max Range: 0.5168. Min Range: -0.5168

Max Act: 0.4424. Min Act: -0.0003

Data Index: 385139 (C4 (Web Text))

Max Activating Token Index: 247

Text #14

Max Range: 0.5168. Min Range: -0.5168

Max Act: 0.4854. Min Act: -0.0003

Data Index: 1271300 (C4 (Web Text))

Max Activating Token Index: 557

Text #15

Max Range: 0.5168. Min Range: -0.5168

Max Act: 0.4784. Min Act: -0.0003

Data Index: 981862 (C4 (Web Text))

Max Activating Token Index: 544

Text #16

Max Range: 0.5168. Min Range: -0.5168

Max Act: 0.4635. Min Act: -0.0003

Data Index: 994724 (C4 (Web Text))

Max Activating Token Index: 43

Text #17

Max Range: 0.5168. Min Range: -0.5168

Max Act: 0.4925. Min Act: -0.0003

Data Index: 1273242 (C4 (Web Text))

Max Activating Token Index: 507

Text #18

Max Range: 0.5168. Min Range: -0.5168

Max Act: 0.4762. Min Act: -0.0003

Data Index: 804881 (C4 (Web Text))

Max Activating Token Index: 276

Text #19

Max Range: 0.5168. Min Range: -0.5168

Max Act: 0.4785. Min Act: -0.0003

Data Index: 1091148 (C4 (Web Text))

Max Activating Token Index: 914