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

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

Neuron 3730 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0009. Min Range: -2.0009

Max Act: 2.0009. Min Act: -0.0000

Data Index: 524355 (C4 (Web Text))

Max Activating Token Index: 211

Text #1

Max Range: 2.0009. Min Range: -2.0009

Max Act: 1.6975. Min Act: -0.0000

Data Index: 262013 (C4 (Web Text))

Max Activating Token Index: 154

Text #2

Max Range: 2.0009. Min Range: -2.0009

Max Act: 1.6388. Min Act: -0.0000

Data Index: 1029663 (C4 (Web Text))

Max Activating Token Index: 488

Text #3

Max Range: 2.0009. Min Range: -2.0009

Max Act: 1.7300. Min Act: -0.0000

Data Index: 475987 (C4 (Web Text))

Max Activating Token Index: 897

Text #4

Max Range: 2.0009. Min Range: -2.0009

Max Act: 1.5791. Min Act: -0.0000

Data Index: 896782 (C4 (Web Text))

Max Activating Token Index: 553

Text #5

Max Range: 2.0009. Min Range: -2.0009

Max Act: 1.5487. Min Act: -0.0000

Data Index: 894925 (C4 (Web Text))

Max Activating Token Index: 286

Text #6

Max Range: 2.0009. Min Range: -2.0009

Max Act: 1.5895. Min Act: -0.0000

Data Index: 1200714 (C4 (Web Text))

Max Activating Token Index: 602

Text #7

Max Range: 2.0009. Min Range: -2.0009

Max Act: 1.5703. Min Act: -0.0000

Data Index: 273199 (C4 (Web Text))

Max Activating Token Index: 733

Text #8

Max Range: 2.0009. Min Range: -2.0009

Max Act: 1.3976. Min Act: -0.0000

Data Index: 637706 (C4 (Web Text))

Max Activating Token Index: 843

Text #9

Max Range: 2.0009. Min Range: -2.0009

Max Act: 1.4843. Min Act: -0.0000

Data Index: 833058 (C4 (Web Text))

Max Activating Token Index: 271

Text #10

Max Range: 2.0009. Min Range: -2.0009

Max Act: 1.4389. Min Act: -0.0000

Data Index: 337818 (C4 (Web Text))

Max Activating Token Index: 756

Text #11

Max Range: 2.0009. Min Range: -2.0009

Max Act: 1.4480. Min Act: -0.0000

Data Index: 506254 (C4 (Web Text))

Max Activating Token Index: 211

Text #12

Max Range: 2.0009. Min Range: -2.0009

Max Act: 1.3877. Min Act: -0.0000

Data Index: 1136515 (C4 (Web Text))

Max Activating Token Index: 238

Text #13

Max Range: 2.0009. Min Range: -2.0009

Max Act: 1.3800. Min Act: -0.0000

Data Index: 356677 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 2.0009. Min Range: -2.0009

Max Act: 1.3618. Min Act: -0.0000

Data Index: 353029 (C4 (Web Text))

Max Activating Token Index: 219

Text #15

Max Range: 2.0009. Min Range: -2.0009

Max Act: 1.3630. Min Act: -0.0000

Data Index: 1185209 (C4 (Web Text))

Max Activating Token Index: 801

Text #16

Max Range: 2.0009. Min Range: -2.0009

Max Act: 1.3839. Min Act: -0.0000

Data Index: 938138 (C4 (Web Text))

Max Activating Token Index: 935

Text #17

Max Range: 2.0009. Min Range: -2.0009

Max Act: 1.2702. Min Act: -0.0000

Data Index: 700537 (C4 (Web Text))

Max Activating Token Index: 227

Text #18

Max Range: 2.0009. Min Range: -2.0009

Max Act: 1.4343. Min Act: -0.0000

Data Index: 686353 (C4 (Web Text))

Max Activating Token Index: 784

Text #19

Max Range: 2.0009. Min Range: -2.0009

Max Act: 1.2585. Min Act: 0.0000

Data Index: 970087 (C4 (Web Text))

Max Activating Token Index: 306