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

Dataset: The Pile

Neuron 2331 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: 2.8080. Min Range: -2.8080

Max Act: 2.8080. Min Act: -0.0000

Data Index: 798843 (The Pile)

Max Activating Token Index: 44

Text #1

Max Range: 2.8080. Min Range: -2.8080

Max Act: 2.4307. Min Act: -0.0000

Data Index: 314115 (The Pile)

Max Activating Token Index: 59

Text #2

Max Range: 2.8080. Min Range: -2.8080

Max Act: 2.6143. Min Act: -0.0000

Data Index: 1700451 (The Pile)

Max Activating Token Index: 54

Text #3

Max Range: 2.8080. Min Range: -2.8080

Max Act: 2.4798. Min Act: -0.0000

Data Index: 1294319 (The Pile)

Max Activating Token Index: 290

Text #4

Max Range: 2.8080. Min Range: -2.8080

Max Act: 2.7338. Min Act: -0.0000

Data Index: 1465046 (The Pile)

Max Activating Token Index: 20

Text #5

Max Range: 2.8080. Min Range: -2.8080

Max Act: 2.5193. Min Act: -0.0000

Data Index: 715294 (The Pile)

Max Activating Token Index: 98

Text #6

Max Range: 2.8080. Min Range: -2.8080

Max Act: 2.4872. Min Act: -0.0000

Data Index: 8665 (The Pile)

Max Activating Token Index: 104

Text #7

Max Range: 2.8080. Min Range: -2.8080

Max Act: 2.6618. Min Act: -0.0000

Data Index: 1535497 (The Pile)

Max Activating Token Index: 61

Text #8

Max Range: 2.8080. Min Range: -2.8080

Max Act: 2.4710. Min Act: -0.0000

Data Index: 361655 (The Pile)

Max Activating Token Index: 78

Text #9

Max Range: 2.8080. Min Range: -2.8080

Max Act: 2.3780. Min Act: -0.0000

Data Index: 1901673 (The Pile)

Max Activating Token Index: 190

Text #10

Max Range: 2.8080. Min Range: -2.8080

Max Act: 2.4656. Min Act: -0.0000

Data Index: 1963005 (The Pile)

Max Activating Token Index: 11

Text #11

Max Range: 2.8080. Min Range: -2.8080

Max Act: 2.4723. Min Act: -0.0000

Data Index: 1612647 (The Pile)

Max Activating Token Index: 234

Text #12

Max Range: 2.8080. Min Range: -2.8080

Max Act: 2.2338. Min Act: -0.0000

Data Index: 939275 (The Pile)

Max Activating Token Index: 201

Text #13

Max Range: 2.8080. Min Range: -2.8080

Max Act: 2.2144. Min Act: -0.0000

Data Index: 1093731 (The Pile)

Max Activating Token Index: 69

Text #14

Max Range: 2.8080. Min Range: -2.8080

Max Act: 2.3363. Min Act: -0.0000

Data Index: 1938170 (The Pile)

Max Activating Token Index: 385

Text #15

Max Range: 2.8080. Min Range: -2.8080

Max Act: 2.3588. Min Act: -0.0000

Data Index: 503065 (The Pile)

Max Activating Token Index: 192

Text #16

Max Range: 2.8080. Min Range: -2.8080

Max Act: 2.7042. Min Act: -0.0000

Data Index: 1452386 (The Pile)

Max Activating Token Index: 134

Text #17

Max Range: 2.8080. Min Range: -2.8080

Max Act: 2.5787. Min Act: -0.0000

Data Index: 1580118 (The Pile)

Max Activating Token Index: 68

Text #18

Max Range: 2.8080. Min Range: -2.8080

Max Act: 2.2747. Min Act: -0.0000

Data Index: 936210 (The Pile)

Max Activating Token Index: 274

Text #19

Max Range: 2.8080. Min Range: -2.8080

Max Act: 2.5222. Min Act: -0.0000

Data Index: 1072454 (The Pile)

Max Activating Token Index: 226