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

Dataset: The Pile

Neuron 3948 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1733. Min Range: -3.1733

Max Act: 3.1733. Min Act: -0.0000

Data Index: 614020 (The Pile)

Max Activating Token Index: 188

Text #1

Max Range: 3.1733. Min Range: -3.1733

Max Act: 3.1499. Min Act: -0.0000

Data Index: 1965105 (The Pile)

Max Activating Token Index: 97

Text #2

Max Range: 3.1733. Min Range: -3.1733

Max Act: 2.9942. Min Act: -0.0000

Data Index: 371749 (The Pile)

Max Activating Token Index: 176

Text #3

Max Range: 3.1733. Min Range: -3.1733

Max Act: 2.6403. Min Act: -0.0000

Data Index: 1517214 (The Pile)

Max Activating Token Index: 258

Text #4

Max Range: 3.1733. Min Range: -3.1733

Max Act: 2.4756. Min Act: -0.0000

Data Index: 294216 (The Pile)

Max Activating Token Index: 306

Text #5

Max Range: 3.1733. Min Range: -3.1733

Max Act: 2.7895. Min Act: -0.0000

Data Index: 1156118 (The Pile)

Max Activating Token Index: 112

Text #6

Max Range: 3.1733. Min Range: -3.1733

Max Act: 2.5991. Min Act: -0.0000

Data Index: 806944 (The Pile)

Max Activating Token Index: 293

Text #7

Max Range: 3.1733. Min Range: -3.1733

Max Act: 2.5927. Min Act: -0.0000

Data Index: 622970 (The Pile)

Max Activating Token Index: 173

Text #8

Max Range: 3.1733. Min Range: -3.1733

Max Act: 2.4764. Min Act: -0.0000

Data Index: 1592142 (The Pile)

Max Activating Token Index: 67

Text #9

Max Range: 3.1733. Min Range: -3.1733

Max Act: 2.7523. Min Act: -0.0000

Data Index: 157602 (The Pile)

Max Activating Token Index: 60

Text #10

Max Range: 3.1733. Min Range: -3.1733

Max Act: 2.5585. Min Act: -0.0000

Data Index: 140495 (The Pile)

Max Activating Token Index: 234

Text #11

Max Range: 3.1733. Min Range: -3.1733

Max Act: 2.3847. Min Act: -0.0000

Data Index: 1762215 (The Pile)

Max Activating Token Index: 260

Text #12

Max Range: 3.1733. Min Range: -3.1733

Max Act: 2.5203. Min Act: -0.0000

Data Index: 518259 (The Pile)

Max Activating Token Index: 277

Text #13

Max Range: 3.1733. Min Range: -3.1733

Max Act: 2.4719. Min Act: -0.0000

Data Index: 997569 (The Pile)

Max Activating Token Index: 133

Text #14

Max Range: 3.1733. Min Range: -3.1733

Max Act: 2.3052. Min Act: -0.0000

Data Index: 1165375 (The Pile)

Max Activating Token Index: 492

Text #15

Max Range: 3.1733. Min Range: -3.1733

Max Act: 2.3029. Min Act: -0.0000

Data Index: 328190 (The Pile)

Max Activating Token Index: 760

Text #16

Max Range: 3.1733. Min Range: -3.1733

Max Act: 2.3985. Min Act: -0.0000

Data Index: 1527785 (The Pile)

Max Activating Token Index: 133

Text #17

Max Range: 3.1733. Min Range: -3.1733

Max Act: 2.4061. Min Act: -0.0000

Data Index: 94597 (The Pile)

Max Activating Token Index: 263

Text #18

Max Range: 3.1733. Min Range: -3.1733

Max Act: 2.5163. Min Act: -0.0000

Data Index: 1101761 (The Pile)

Max Activating Token Index: 216

Text #19

Max Range: 3.1733. Min Range: -3.1733

Max Act: 2.3853. Min Act: -0.0000

Data Index: 990090 (The Pile)

Max Activating Token Index: 334