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

Dataset: The Pile

Neuron 4647 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: 1.5758. Min Range: -1.5758

Max Act: 1.5758. Min Act: -0.0000

Data Index: 260738 (The Pile)

Max Activating Token Index: 64

Text #1

Max Range: 1.5758. Min Range: -1.5758

Max Act: 0.8577. Min Act: -0.0000

Data Index: 68158 (The Pile)

Max Activating Token Index: 309

Text #2

Max Range: 1.5758. Min Range: -1.5758

Max Act: 0.7528. Min Act: -0.0000

Data Index: 476659 (The Pile)

Max Activating Token Index: 879

Text #3

Max Range: 1.5758. Min Range: -1.5758

Max Act: 0.7048. Min Act: -0.0000

Data Index: 535244 (The Pile)

Max Activating Token Index: 592

Text #4

Max Range: 1.5758. Min Range: -1.5758

Max Act: 0.7387. Min Act: -0.0000

Data Index: 1297397 (The Pile)

Max Activating Token Index: 124

Text #5

Max Range: 1.5758. Min Range: -1.5758

Max Act: 0.6212. Min Act: -0.0000

Data Index: 1836968 (The Pile)

Max Activating Token Index: 103

Text #6

Max Range: 1.5758. Min Range: -1.5758

Max Act: 0.6723. Min Act: -0.0000

Data Index: 1398967 (The Pile)

Max Activating Token Index: 13

Text #7

Max Range: 1.5758. Min Range: -1.5758

Max Act: 0.6587. Min Act: -0.0000

Data Index: 1458127 (The Pile)

Max Activating Token Index: 590

Text #8

Max Range: 1.5758. Min Range: -1.5758

Max Act: 0.6516. Min Act: -0.0000

Data Index: 306120 (The Pile)

Max Activating Token Index: 317

Text #9

Max Range: 1.5758. Min Range: -1.5758

Max Act: 0.6710. Min Act: -0.0000

Data Index: 1585883 (The Pile)

Max Activating Token Index: 97

Text #10

Max Range: 1.5758. Min Range: -1.5758

Max Act: 0.6438. Min Act: -0.0000

Data Index: 1262193 (The Pile)

Max Activating Token Index: 31

Text #11

Max Range: 1.5758. Min Range: -1.5758

Max Act: 0.6060. Min Act: -0.0000

Data Index: 436660 (The Pile)

Max Activating Token Index: 1007

Text #12

Max Range: 1.5758. Min Range: -1.5758

Max Act: 0.6575. Min Act: -0.0000

Data Index: 384532 (The Pile)

Max Activating Token Index: 178

Text #13

Max Range: 1.5758. Min Range: -1.5758

Max Act: 0.6099. Min Act: -0.0000

Data Index: 888646 (The Pile)

Max Activating Token Index: 82

Text #14

Max Range: 1.5758. Min Range: -1.5758

Max Act: 0.6245. Min Act: -0.0000

Data Index: 1701697 (The Pile)

Max Activating Token Index: 67

Text #15

Max Range: 1.5758. Min Range: -1.5758

Max Act: 0.6193. Min Act: -0.0000

Data Index: 1114422 (The Pile)

Max Activating Token Index: 701

Text #16

Max Range: 1.5758. Min Range: -1.5758

Max Act: 0.5925. Min Act: -0.0000

Data Index: 1839945 (The Pile)

Max Activating Token Index: 254

Text #17

Max Range: 1.5758. Min Range: -1.5758

Max Act: 0.5753. Min Act: -0.0000

Data Index: 529926 (The Pile)

Max Activating Token Index: 1004

Text #18

Max Range: 1.5758. Min Range: -1.5758

Max Act: 0.5854. Min Act: -0.0000

Data Index: 1551904 (The Pile)

Max Activating Token Index: 452

Text #19

Max Range: 1.5758. Min Range: -1.5758

Max Act: 0.5555. Min Act: -0.0000

Data Index: 1027890 (The Pile)

Max Activating Token Index: 402