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

Dataset: The Pile

Neuron 4514 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.8081. Min Act: -0.0000

Data Index: 500088 (The Pile)

Max Activating Token Index: 972

Text #1

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.6308. Min Act: -0.0000

Data Index: 1623920 (The Pile)

Max Activating Token Index: 800

Text #2

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.6382. Min Act: -0.0000

Data Index: 18516 (The Pile)

Max Activating Token Index: 259

Text #3

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.6497. Min Act: -0.0000

Data Index: 1216940 (The Pile)

Max Activating Token Index: 498

Text #4

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.7041. Min Act: -0.0000

Data Index: 1413055 (The Pile)

Max Activating Token Index: 838

Text #5

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.5871. Min Act: -0.0000

Data Index: 97849 (The Pile)

Max Activating Token Index: 533

Text #6

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.6166. Min Act: -0.0000

Data Index: 697723 (The Pile)

Max Activating Token Index: 949

Text #7

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.4920. Min Act: -0.0000

Data Index: 647650 (The Pile)

Max Activating Token Index: 125

Text #8

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.5383. Min Act: -0.0000

Data Index: 1257685 (The Pile)

Max Activating Token Index: 808

Text #9

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.5287. Min Act: -0.0000

Data Index: 984391 (The Pile)

Max Activating Token Index: 381

Text #10

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.5198. Min Act: -0.0000

Data Index: 222134 (The Pile)

Max Activating Token Index: 50

Text #11

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.5066. Min Act: -0.0000

Data Index: 1217748 (The Pile)

Max Activating Token Index: 726

Text #12

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.4962. Min Act: -0.0000

Data Index: 1809115 (The Pile)

Max Activating Token Index: 31

Text #13

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.4832. Min Act: -0.0000

Data Index: 986992 (The Pile)

Max Activating Token Index: 267

Text #14

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.4611. Min Act: -0.0000

Data Index: 583705 (The Pile)

Max Activating Token Index: 917

Text #15

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.4639. Min Act: -0.0000

Data Index: 367155 (The Pile)

Max Activating Token Index: 121

Text #16

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.4603. Min Act: -0.0000

Data Index: 64737 (The Pile)

Max Activating Token Index: 480

Text #17

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.4598. Min Act: -0.0000

Data Index: 1174803 (The Pile)

Max Activating Token Index: 641

Text #18

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.4929. Min Act: -0.0000

Data Index: 1954326 (The Pile)

Max Activating Token Index: 546

Text #19

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.4243. Min Act: -0.0000

Data Index: 324969 (The Pile)

Max Activating Token Index: 840