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

Dataset: The Pile

Neuron 1948 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: 0.7089. Min Range: -0.7089

Max Act: 0.7089. Min Act: -0.0000

Data Index: 777518 (The Pile)

Max Activating Token Index: 729

Text #1

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.6826. Min Act: -0.0000

Data Index: 406134 (The Pile)

Max Activating Token Index: 303

Text #2

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.5944. Min Act: -0.0000

Data Index: 366656 (The Pile)

Max Activating Token Index: 92

Text #3

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.4995. Min Act: -0.0000

Data Index: 932592 (The Pile)

Max Activating Token Index: 126

Text #4

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.4806. Min Act: -0.0000

Data Index: 167799 (The Pile)

Max Activating Token Index: 171

Text #5

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.5004. Min Act: -0.0000

Data Index: 1764674 (The Pile)

Max Activating Token Index: 443

Text #6

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.5041. Min Act: -0.0000

Data Index: 847226 (The Pile)

Max Activating Token Index: 437

Text #7

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.4820. Min Act: -0.0000

Data Index: 1884628 (The Pile)

Max Activating Token Index: 724

Text #8

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.4561. Min Act: -0.0000

Data Index: 64193 (The Pile)

Max Activating Token Index: 532

Text #9

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.4476. Min Act: -0.0000

Data Index: 504119 (The Pile)

Max Activating Token Index: 532

Text #10

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.4545. Min Act: -0.0000

Data Index: 33773 (The Pile)

Max Activating Token Index: 447

Text #11

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.3901. Min Act: -0.0000

Data Index: 924926 (The Pile)

Max Activating Token Index: 899

Text #12

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.4311. Min Act: -0.0000

Data Index: 41906 (The Pile)

Max Activating Token Index: 816

Text #13

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.3883. Min Act: -0.0000

Data Index: 417110 (The Pile)

Max Activating Token Index: 898

Text #14

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.4062. Min Act: -0.0000

Data Index: 1894116 (The Pile)

Max Activating Token Index: 998

Text #15

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.4105. Min Act: -0.0000

Data Index: 828355 (The Pile)

Max Activating Token Index: 498

Text #16

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.4145. Min Act: -0.0000

Data Index: 1218788 (The Pile)

Max Activating Token Index: 734

Text #17

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.3688. Min Act: -0.0000

Data Index: 1824235 (The Pile)

Max Activating Token Index: 694

Text #18

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.4003. Min Act: -0.0000

Data Index: 458112 (The Pile)

Max Activating Token Index: 224

Text #19

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.3676. Min Act: -0.0000

Data Index: 191334 (The Pile)

Max Activating Token Index: 81