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

Dataset: The Pile

Neuron 4731 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3080. Min Range: -4.3080

Max Act: 4.3080. Min Act: -0.0000

Data Index: 219665 (The Pile)

Max Activating Token Index: 698

Text #1

Max Range: 4.3080. Min Range: -4.3080

Max Act: 3.8766. Min Act: -0.0000

Data Index: 1417395 (The Pile)

Max Activating Token Index: 996

Text #2

Max Range: 4.3080. Min Range: -4.3080

Max Act: 3.5748. Min Act: -0.0000

Data Index: 537466 (The Pile)

Max Activating Token Index: 355

Text #3

Max Range: 4.3080. Min Range: -4.3080

Max Act: 2.7242. Min Act: -0.0000

Data Index: 1520412 (The Pile)

Max Activating Token Index: 754

Text #4

Max Range: 4.3080. Min Range: -4.3080

Max Act: 3.2179. Min Act: -0.0000

Data Index: 1064116 (The Pile)

Max Activating Token Index: 855

Text #5

Max Range: 4.3080. Min Range: -4.3080

Max Act: 3.2754. Min Act: -0.0000

Data Index: 1454265 (The Pile)

Max Activating Token Index: 393

Text #6

Max Range: 4.3080. Min Range: -4.3080

Max Act: 3.2783. Min Act: -0.0000

Data Index: 1211738 (The Pile)

Max Activating Token Index: 333

Text #7

Max Range: 4.3080. Min Range: -4.3080

Max Act: 3.2698. Min Act: -0.0000

Data Index: 517702 (The Pile)

Max Activating Token Index: 163

Text #8

Max Range: 4.3080. Min Range: -4.3080

Max Act: 3.2635. Min Act: -0.0000

Data Index: 1508169 (The Pile)

Max Activating Token Index: 49

Text #9

Max Range: 4.3080. Min Range: -4.3080

Max Act: 3.0429. Min Act: -0.0000

Data Index: 1829108 (The Pile)

Max Activating Token Index: 328

Text #10

Max Range: 4.3080. Min Range: -4.3080

Max Act: 3.1727. Min Act: -0.0000

Data Index: 1056109 (The Pile)

Max Activating Token Index: 516

Text #11

Max Range: 4.3080. Min Range: -4.3080

Max Act: 3.1593. Min Act: -0.0000

Data Index: 1305687 (The Pile)

Max Activating Token Index: 105

Text #12

Max Range: 4.3080. Min Range: -4.3080

Max Act: 3.3206. Min Act: -0.0000

Data Index: 1891421 (The Pile)

Max Activating Token Index: 331

Text #13

Max Range: 4.3080. Min Range: -4.3080

Max Act: 2.9281. Min Act: -0.0000

Data Index: 1640313 (The Pile)

Max Activating Token Index: 459

Text #14

Max Range: 4.3080. Min Range: -4.3080

Max Act: 3.0816. Min Act: -0.0000

Data Index: 171381 (The Pile)

Max Activating Token Index: 238

Text #15

Max Range: 4.3080. Min Range: -4.3080

Max Act: 2.9403. Min Act: -0.0000

Data Index: 1910963 (The Pile)

Max Activating Token Index: 116

Text #16

Max Range: 4.3080. Min Range: -4.3080

Max Act: 3.0349. Min Act: -0.0000

Data Index: 1646859 (The Pile)

Max Activating Token Index: 314

Text #17

Max Range: 4.3080. Min Range: -4.3080

Max Act: 3.1068. Min Act: -0.0000

Data Index: 536837 (The Pile)

Max Activating Token Index: 1000

Text #18

Max Range: 4.3080. Min Range: -4.3080

Max Act: 2.7212. Min Act: -0.0000

Data Index: 1514351 (The Pile)

Max Activating Token Index: 746

Text #19

Max Range: 4.3080. Min Range: -4.3080

Max Act: 3.0881. Min Act: -0.0000

Data Index: 882306 (The Pile)

Max Activating Token Index: 533