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

Dataset: The Pile

Neuron 2129 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.9399. Min Act: -0.0000

Data Index: 533421 (The Pile)

Max Activating Token Index: 662

Text #1

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.9281. Min Act: -0.0000

Data Index: 376437 (The Pile)

Max Activating Token Index: 641

Text #2

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.9649. Min Act: -0.0000

Data Index: 355441 (The Pile)

Max Activating Token Index: 570

Text #3

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.8427. Min Act: -0.0000

Data Index: 1843580 (The Pile)

Max Activating Token Index: 187

Text #4

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.8126. Min Act: -0.0000

Data Index: 200112 (The Pile)

Max Activating Token Index: 681

Text #5

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.9171. Min Act: -0.0000

Data Index: 1017208 (The Pile)

Max Activating Token Index: 929

Text #6

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.8945. Min Act: -0.0000

Data Index: 1886678 (The Pile)

Max Activating Token Index: 411

Text #7

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.8593. Min Act: -0.0000

Data Index: 511074 (The Pile)

Max Activating Token Index: 672

Text #8

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.8870. Min Act: -0.0000

Data Index: 1320290 (The Pile)

Max Activating Token Index: 798

Text #9

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.8094. Min Act: -0.0000

Data Index: 870272 (The Pile)

Max Activating Token Index: 859

Text #10

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.8589. Min Act: -0.0000

Data Index: 1105518 (The Pile)

Max Activating Token Index: 133

Text #11

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.8503. Min Act: -0.0000

Data Index: 161651 (The Pile)

Max Activating Token Index: 865

Text #12

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.7362. Min Act: -0.0000

Data Index: 303949 (The Pile)

Max Activating Token Index: 626

Text #13

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.9063. Min Act: -0.0000

Data Index: 1565639 (The Pile)

Max Activating Token Index: 549

Text #14

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.8486. Min Act: -0.0000

Data Index: 1193319 (The Pile)

Max Activating Token Index: 741

Text #15

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.8169. Min Act: -0.0000

Data Index: 1680756 (The Pile)

Max Activating Token Index: 546

Text #16

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.8392. Min Act: -0.0000

Data Index: 1274322 (The Pile)

Max Activating Token Index: 594

Text #17

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.8093. Min Act: -0.0000

Data Index: 1155524 (The Pile)

Max Activating Token Index: 251

Text #18

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.8655. Min Act: -0.0000

Data Index: 671248 (The Pile)

Max Activating Token Index: 195

Text #19

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.7556. Min Act: -0.0000

Data Index: 414245 (The Pile)

Max Activating Token Index: 330