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

Dataset: The Pile

Neuron 376 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: 0.6940. Min Range: -0.6940

Max Act: 0.6820. Min Act: -0.0000

Data Index: 32494 (The Pile)

Max Activating Token Index: 178

Text #1

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.6191. Min Act: -0.0000

Data Index: 551355 (The Pile)

Max Activating Token Index: 942

Text #2

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.6940. Min Act: -0.0000

Data Index: 501148 (The Pile)

Max Activating Token Index: 496

Text #3

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.5980. Min Act: -0.0000

Data Index: 356295 (The Pile)

Max Activating Token Index: 39

Text #4

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.5579. Min Act: -0.0000

Data Index: 1347539 (The Pile)

Max Activating Token Index: 82

Text #5

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.5904. Min Act: -0.0000

Data Index: 1957031 (The Pile)

Max Activating Token Index: 269

Text #6

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.5857. Min Act: -0.0000

Data Index: 1631084 (The Pile)

Max Activating Token Index: 202

Text #7

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.6080. Min Act: -0.0000

Data Index: 601404 (The Pile)

Max Activating Token Index: 682

Text #8

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.5310. Min Act: -0.0000

Data Index: 440518 (The Pile)

Max Activating Token Index: 604

Text #9

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.5465. Min Act: -0.0000

Data Index: 1408627 (The Pile)

Max Activating Token Index: 722

Text #10

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.4782. Min Act: -0.0000

Data Index: 1275340 (The Pile)

Max Activating Token Index: 118

Text #11

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.5104. Min Act: -0.0000

Data Index: 930354 (The Pile)

Max Activating Token Index: 162

Text #12

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.5155. Min Act: -0.0000

Data Index: 1342683 (The Pile)

Max Activating Token Index: 379

Text #13

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.5329. Min Act: -0.0000

Data Index: 748203 (The Pile)

Max Activating Token Index: 301

Text #14

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.5377. Min Act: -0.0000

Data Index: 1346683 (The Pile)

Max Activating Token Index: 682

Text #15

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.5165. Min Act: -0.0000

Data Index: 415846 (The Pile)

Max Activating Token Index: 318

Text #16

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.4132. Min Act: -0.0000

Data Index: 1857222 (The Pile)

Max Activating Token Index: 635

Text #17

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.4994. Min Act: -0.0000

Data Index: 587791 (The Pile)

Max Activating Token Index: 654

Text #18

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.5290. Min Act: -0.0000

Data Index: 82347 (The Pile)

Max Activating Token Index: 719

Text #19

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.4903. Min Act: -0.0000

Data Index: 982249 (The Pile)

Max Activating Token Index: 802