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

Dataset: The Pile

Neuron 4515 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5277. Min Range: -3.5277

Max Act: 3.5277. Min Act: -0.0000

Data Index: 869523 (The Pile)

Max Activating Token Index: 6

Text #1

Max Range: 3.5277. Min Range: -3.5277

Max Act: 3.3313. Min Act: -0.0000

Data Index: 1549066 (The Pile)

Max Activating Token Index: 364

Text #2

Max Range: 3.5277. Min Range: -3.5277

Max Act: 3.2076. Min Act: -0.0000

Data Index: 209416 (The Pile)

Max Activating Token Index: 995

Text #3

Max Range: 3.5277. Min Range: -3.5277

Max Act: 3.2879. Min Act: -0.0000

Data Index: 601505 (The Pile)

Max Activating Token Index: 842

Text #4

Max Range: 3.5277. Min Range: -3.5277

Max Act: 3.1216. Min Act: -0.0000

Data Index: 325115 (The Pile)

Max Activating Token Index: 759

Text #5

Max Range: 3.5277. Min Range: -3.5277

Max Act: 3.1281. Min Act: -0.0000

Data Index: 468020 (The Pile)

Max Activating Token Index: 35

Text #6

Max Range: 3.5277. Min Range: -3.5277

Max Act: 3.0598. Min Act: -0.0000

Data Index: 899284 (The Pile)

Max Activating Token Index: 988

Text #7

Max Range: 3.5277. Min Range: -3.5277

Max Act: 3.0061. Min Act: -0.0000

Data Index: 424459 (The Pile)

Max Activating Token Index: 147

Text #8

Max Range: 3.5277. Min Range: -3.5277

Max Act: 2.9470. Min Act: -0.0000

Data Index: 1994771 (The Pile)

Max Activating Token Index: 635

Text #9

Max Range: 3.5277. Min Range: -3.5277

Max Act: 2.9540. Min Act: -0.0000

Data Index: 348572 (The Pile)

Max Activating Token Index: 74

Text #10

Max Range: 3.5277. Min Range: -3.5277

Max Act: 2.9216. Min Act: -0.0000

Data Index: 1154852 (The Pile)

Max Activating Token Index: 40

Text #11

Max Range: 3.5277. Min Range: -3.5277

Max Act: 2.8969. Min Act: -0.0000

Data Index: 1790929 (The Pile)

Max Activating Token Index: 544

Text #12

Max Range: 3.5277. Min Range: -3.5277

Max Act: 2.8799. Min Act: -0.0000

Data Index: 1268993 (The Pile)

Max Activating Token Index: 44

Text #13

Max Range: 3.5277. Min Range: -3.5277

Max Act: 2.8906. Min Act: -0.0000

Data Index: 1823107 (The Pile)

Max Activating Token Index: 892

Text #14

Max Range: 3.5277. Min Range: -3.5277

Max Act: 2.9060. Min Act: -0.0000

Data Index: 779630 (The Pile)

Max Activating Token Index: 944

Text #15

Max Range: 3.5277. Min Range: -3.5277

Max Act: 2.8702. Min Act: -0.0000

Data Index: 463759 (The Pile)

Max Activating Token Index: 224

Text #16

Max Range: 3.5277. Min Range: -3.5277

Max Act: 2.8530. Min Act: -0.0000

Data Index: 1643595 (The Pile)

Max Activating Token Index: 185

Text #17

Max Range: 3.5277. Min Range: -3.5277

Max Act: 2.8741. Min Act: -0.0000

Data Index: 1631813 (The Pile)

Max Activating Token Index: 976

Text #18

Max Range: 3.5277. Min Range: -3.5277

Max Act: 2.8721. Min Act: -0.0000

Data Index: 780148 (The Pile)

Max Activating Token Index: 435

Text #19

Max Range: 3.5277. Min Range: -3.5277

Max Act: 2.8650. Min Act: -0.0000

Data Index: 1287738 (The Pile)

Max Activating Token Index: 210