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

Dataset: The Pile

Neuron 1670 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.5883. Min Act: 0.0000

Data Index: 469655 (The Pile)

Max Activating Token Index: 235

Text #1

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.5800. Min Act: 0.0000

Data Index: 190342 (The Pile)

Max Activating Token Index: 115

Text #2

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.5532. Min Act: -0.0000

Data Index: 385019 (The Pile)

Max Activating Token Index: 490

Text #3

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.5132. Min Act: -0.0000

Data Index: 680367 (The Pile)

Max Activating Token Index: 500

Text #4

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.4933. Min Act: -0.0000

Data Index: 1685867 (The Pile)

Max Activating Token Index: 453

Text #5

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.4965. Min Act: -0.0000

Data Index: 330803 (The Pile)

Max Activating Token Index: 879

Text #6

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.4450. Min Act: -0.0000

Data Index: 1472369 (The Pile)

Max Activating Token Index: 668

Text #7

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.4609. Min Act: 0.0000

Data Index: 1113558 (The Pile)

Max Activating Token Index: 601

Text #8

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.4313. Min Act: -0.0000

Data Index: 1970028 (The Pile)

Max Activating Token Index: 994

Text #9

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.4598. Min Act: -0.0000

Data Index: 1759877 (The Pile)

Max Activating Token Index: 776

Text #10

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.4422. Min Act: -0.0000

Data Index: 1554134 (The Pile)

Max Activating Token Index: 878

Text #11

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.4198. Min Act: -0.0000

Data Index: 1291046 (The Pile)

Max Activating Token Index: 264

Text #12

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.4274. Min Act: -0.0000

Data Index: 297584 (The Pile)

Max Activating Token Index: 418

Text #13

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.4270. Min Act: -0.0000

Data Index: 1721113 (The Pile)

Max Activating Token Index: 965

Text #14

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.4204. Min Act: -0.0000

Data Index: 1417111 (The Pile)

Max Activating Token Index: 528

Text #15

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.4184. Min Act: 0.0000

Data Index: 1017047 (The Pile)

Max Activating Token Index: 390

Text #16

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.4021. Min Act: -0.0000

Data Index: 1988039 (The Pile)

Max Activating Token Index: 1006

Text #17

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.4032. Min Act: -0.0000

Data Index: 1088116 (The Pile)

Max Activating Token Index: 479

Text #18

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.4157. Min Act: -0.0000

Data Index: 674787 (The Pile)

Max Activating Token Index: 322

Text #19

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.3759. Min Act: -0.0000

Data Index: 1383925 (The Pile)

Max Activating Token Index: 992