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

Dataset: The Pile

Neuron 282 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.6981. Min Act: 0.0000

Data Index: 1574951 (The Pile)

Max Activating Token Index: 840

Text #1

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.7051. Min Act: -0.0000

Data Index: 200740 (The Pile)

Max Activating Token Index: 201

Text #2

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.6809. Min Act: -0.0000

Data Index: 424232 (The Pile)

Max Activating Token Index: 435

Text #3

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.6952. Min Act: -0.0000

Data Index: 757303 (The Pile)

Max Activating Token Index: 492

Text #4

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.6665. Min Act: -0.0000

Data Index: 1639352 (The Pile)

Max Activating Token Index: 211

Text #5

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.6458. Min Act: -0.0000

Data Index: 404967 (The Pile)

Max Activating Token Index: 256

Text #6

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.6459. Min Act: -0.0000

Data Index: 228500 (The Pile)

Max Activating Token Index: 435

Text #7

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.6404. Min Act: -0.0000

Data Index: 1633542 (The Pile)

Max Activating Token Index: 603

Text #8

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.6360. Min Act: -0.0000

Data Index: 1091556 (The Pile)

Max Activating Token Index: 111

Text #9

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.6373. Min Act: -0.0000

Data Index: 1414494 (The Pile)

Max Activating Token Index: 145

Text #10

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.6315. Min Act: -0.0000

Data Index: 1935369 (The Pile)

Max Activating Token Index: 726

Text #11

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.6283. Min Act: -0.0000

Data Index: 782235 (The Pile)

Max Activating Token Index: 396

Text #12

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.6125. Min Act: -0.0000

Data Index: 1761008 (The Pile)

Max Activating Token Index: 612

Text #13

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.6303. Min Act: -0.0000

Data Index: 883622 (The Pile)

Max Activating Token Index: 354

Text #14

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.5828. Min Act: -0.0000

Data Index: 1354861 (The Pile)

Max Activating Token Index: 512

Text #15

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.6025. Min Act: -0.0000

Data Index: 1992481 (The Pile)

Max Activating Token Index: 727

Text #16

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.6088. Min Act: -0.0000

Data Index: 1503679 (The Pile)

Max Activating Token Index: 176

Text #17

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.5933. Min Act: -0.0000

Data Index: 873801 (The Pile)

Max Activating Token Index: 729

Text #18

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.5824. Min Act: -0.0000

Data Index: 1678288 (The Pile)

Max Activating Token Index: 530

Text #19

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.5833. Min Act: -0.0000

Data Index: 1989912 (The Pile)

Max Activating Token Index: 776