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

Dataset: The Pile

Neuron 769 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9247. Min Range: -5.9247

Max Act: 5.9247. Min Act: -0.0000

Data Index: 1951680 (The Pile)

Max Activating Token Index: 692

Text #1

Max Range: 5.9247. Min Range: -5.9247

Max Act: 5.3734. Min Act: -0.0000

Data Index: 26688 (The Pile)

Max Activating Token Index: 638

Text #2

Max Range: 5.9247. Min Range: -5.9247

Max Act: 5.3199. Min Act: -0.0000

Data Index: 1967145 (The Pile)

Max Activating Token Index: 223

Text #3

Max Range: 5.9247. Min Range: -5.9247

Max Act: 5.5100. Min Act: -0.0000

Data Index: 1882393 (The Pile)

Max Activating Token Index: 38

Text #4

Max Range: 5.9247. Min Range: -5.9247

Max Act: 5.2528. Min Act: -0.0000

Data Index: 305601 (The Pile)

Max Activating Token Index: 601

Text #5

Max Range: 5.9247. Min Range: -5.9247

Max Act: 5.1991. Min Act: -0.0000

Data Index: 452009 (The Pile)

Max Activating Token Index: 318

Text #6

Max Range: 5.9247. Min Range: -5.9247

Max Act: 4.9440. Min Act: -0.0000

Data Index: 633550 (The Pile)

Max Activating Token Index: 509

Text #7

Max Range: 5.9247. Min Range: -5.9247

Max Act: 4.6775. Min Act: -0.0000

Data Index: 914289 (The Pile)

Max Activating Token Index: 33

Text #8

Max Range: 5.9247. Min Range: -5.9247

Max Act: 5.0256. Min Act: -0.0000

Data Index: 117472 (The Pile)

Max Activating Token Index: 516

Text #9

Max Range: 5.9247. Min Range: -5.9247

Max Act: 5.2213. Min Act: -0.0000

Data Index: 1666351 (The Pile)

Max Activating Token Index: 124

Text #10

Max Range: 5.9247. Min Range: -5.9247

Max Act: 5.0213. Min Act: -0.0000

Data Index: 1026054 (The Pile)

Max Activating Token Index: 810

Text #11

Max Range: 5.9247. Min Range: -5.9247

Max Act: 5.1285. Min Act: -0.0000

Data Index: 1936389 (The Pile)

Max Activating Token Index: 987

Text #12

Max Range: 5.9247. Min Range: -5.9247

Max Act: 4.7230. Min Act: -0.0000

Data Index: 1228467 (The Pile)

Max Activating Token Index: 734

Text #13

Max Range: 5.9247. Min Range: -5.9247

Max Act: 4.5268. Min Act: -0.0000

Data Index: 1377358 (The Pile)

Max Activating Token Index: 923

Text #14

Max Range: 5.9247. Min Range: -5.9247

Max Act: 4.8748. Min Act: -0.0000

Data Index: 1532604 (The Pile)

Max Activating Token Index: 22

Text #15

Max Range: 5.9247. Min Range: -5.9247

Max Act: 4.8689. Min Act: -0.0000

Data Index: 834531 (The Pile)

Max Activating Token Index: 658

Text #16

Max Range: 5.9247. Min Range: -5.9247

Max Act: 4.6764. Min Act: -0.0000

Data Index: 1377487 (The Pile)

Max Activating Token Index: 267

Text #17

Max Range: 5.9247. Min Range: -5.9247

Max Act: 4.9855. Min Act: -0.0000

Data Index: 155958 (The Pile)

Max Activating Token Index: 1005

Text #18

Max Range: 5.9247. Min Range: -5.9247

Max Act: 4.5975. Min Act: -0.0000

Data Index: 948434 (The Pile)

Max Activating Token Index: 313

Text #19

Max Range: 5.9247. Min Range: -5.9247

Max Act: 4.9513. Min Act: -0.0000

Data Index: 1812834 (The Pile)

Max Activating Token Index: 60