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

Dataset: The Pile

Neuron 3900 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0187. Min Range: -1.0187

Max Act: 1.0187. Min Act: -0.0000

Data Index: 1534787 (The Pile)

Max Activating Token Index: 624

Text #1

Max Range: 1.0187. Min Range: -1.0187

Max Act: 0.6913. Min Act: 0.0000

Data Index: 1767920 (The Pile)

Max Activating Token Index: 193

Text #2

Max Range: 1.0187. Min Range: -1.0187

Max Act: 0.6745. Min Act: -0.0000

Data Index: 1030995 (The Pile)

Max Activating Token Index: 901

Text #3

Max Range: 1.0187. Min Range: -1.0187

Max Act: 0.6388. Min Act: -0.0000

Data Index: 1688758 (The Pile)

Max Activating Token Index: 739

Text #4

Max Range: 1.0187. Min Range: -1.0187

Max Act: 0.6100. Min Act: -0.0000

Data Index: 528175 (The Pile)

Max Activating Token Index: 119

Text #5

Max Range: 1.0187. Min Range: -1.0187

Max Act: 0.6051. Min Act: -0.0000

Data Index: 1703872 (The Pile)

Max Activating Token Index: 324

Text #6

Max Range: 1.0187. Min Range: -1.0187

Max Act: 0.5938. Min Act: -0.0000

Data Index: 267957 (The Pile)

Max Activating Token Index: 125

Text #7

Max Range: 1.0187. Min Range: -1.0187

Max Act: 0.5410. Min Act: -0.0000

Data Index: 1458359 (The Pile)

Max Activating Token Index: 115

Text #8

Max Range: 1.0187. Min Range: -1.0187

Max Act: 0.5595. Min Act: 0.0000

Data Index: 879762 (The Pile)

Max Activating Token Index: 258

Text #9

Max Range: 1.0187. Min Range: -1.0187

Max Act: 0.5134. Min Act: 0.0000

Data Index: 265810 (The Pile)

Max Activating Token Index: 499

Text #10

Max Range: 1.0187. Min Range: -1.0187

Max Act: 0.5175. Min Act: -0.0000

Data Index: 1410807 (The Pile)

Max Activating Token Index: 298

Text #11

Max Range: 1.0187. Min Range: -1.0187

Max Act: 0.4987. Min Act: -0.0000

Data Index: 230027 (The Pile)

Max Activating Token Index: 67

Text #12

Max Range: 1.0187. Min Range: -1.0187

Max Act: 0.4473. Min Act: -0.0000

Data Index: 1121537 (The Pile)

Max Activating Token Index: 722

Text #13

Max Range: 1.0187. Min Range: -1.0187

Max Act: 0.4781. Min Act: -0.0000

Data Index: 1365022 (The Pile)

Max Activating Token Index: 1016

Text #14

Max Range: 1.0187. Min Range: -1.0187

Max Act: 0.5569. Min Act: -0.0001

Data Index: 997658 (The Pile)

Max Activating Token Index: 437

Text #15

Max Range: 1.0187. Min Range: -1.0187

Max Act: 0.4780. Min Act: -0.0000

Data Index: 1634424 (The Pile)

Max Activating Token Index: 885

Text #16

Max Range: 1.0187. Min Range: -1.0187

Max Act: 0.4714. Min Act: -0.0000

Data Index: 398449 (The Pile)

Max Activating Token Index: 337

Text #17

Max Range: 1.0187. Min Range: -1.0187

Max Act: 0.4577. Min Act: -0.0000

Data Index: 1069754 (The Pile)

Max Activating Token Index: 964

Text #18

Max Range: 1.0187. Min Range: -1.0187

Max Act: 0.5228. Min Act: -0.0000

Data Index: 403241 (The Pile)

Max Activating Token Index: 693

Text #19

Max Range: 1.0187. Min Range: -1.0187

Max Act: 0.4957. Min Act: -0.0000

Data Index: 221145 (The Pile)

Max Activating Token Index: 323