Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 696 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.3834. Min Range: -0.3834

Max Act: 0.3834. Min Act: -0.0000

Data Index: 204420 (The Pile)

Max Activating Token Index: 396

Text #1

Max Range: 0.3834. Min Range: -0.3834

Max Act: 0.3549. Min Act: -0.0000

Data Index: 1416206 (The Pile)

Max Activating Token Index: 944

Text #2

Max Range: 0.3834. Min Range: -0.3834

Max Act: 0.3800. Min Act: -0.0000

Data Index: 620064 (The Pile)

Max Activating Token Index: 166

Text #3

Max Range: 0.3834. Min Range: -0.3834

Max Act: 0.3624. Min Act: -0.0000

Data Index: 1700598 (The Pile)

Max Activating Token Index: 7

Text #4

Max Range: 0.3834. Min Range: -0.3834

Max Act: 0.3370. Min Act: -0.0000

Data Index: 1573429 (The Pile)

Max Activating Token Index: 741

Text #5

Max Range: 0.3834. Min Range: -0.3834

Max Act: 0.3463. Min Act: -0.0000

Data Index: 132799 (The Pile)

Max Activating Token Index: 1022

Text #6

Max Range: 0.3834. Min Range: -0.3834

Max Act: 0.3036. Min Act: -0.0000

Data Index: 354677 (The Pile)

Max Activating Token Index: 194

Text #7

Max Range: 0.3834. Min Range: -0.3834

Max Act: 0.3557. Min Act: -0.0000

Data Index: 762158 (The Pile)

Max Activating Token Index: 1010

Text #8

Max Range: 0.3834. Min Range: -0.3834

Max Act: 0.2921. Min Act: -0.0000

Data Index: 767402 (The Pile)

Max Activating Token Index: 67

Text #9

Max Range: 0.3834. Min Range: -0.3834

Max Act: 0.3039. Min Act: -0.0000

Data Index: 103759 (The Pile)

Max Activating Token Index: 74

Text #10

Max Range: 0.3834. Min Range: -0.3834

Max Act: 0.3111. Min Act: -0.0000

Data Index: 1923299 (The Pile)

Max Activating Token Index: 16

Text #11

Max Range: 0.3834. Min Range: -0.3834

Max Act: 0.3173. Min Act: -0.0000

Data Index: 1036994 (The Pile)

Max Activating Token Index: 195

Text #12

Max Range: 0.3834. Min Range: -0.3834

Max Act: 0.3053. Min Act: -0.0000

Data Index: 1146664 (The Pile)

Max Activating Token Index: 803

Text #13

Max Range: 0.3834. Min Range: -0.3834

Max Act: 0.3257. Min Act: -0.0000

Data Index: 1192644 (The Pile)

Max Activating Token Index: 85

Text #14

Max Range: 0.3834. Min Range: -0.3834

Max Act: 0.3034. Min Act: -0.0000

Data Index: 258866 (The Pile)

Max Activating Token Index: 532

Text #15

Max Range: 0.3834. Min Range: -0.3834

Max Act: 0.2710. Min Act: -0.0000

Data Index: 1055669 (The Pile)

Max Activating Token Index: 654

Text #16

Max Range: 0.3834. Min Range: -0.3834

Max Act: 0.2919. Min Act: -0.0000

Data Index: 1194577 (The Pile)

Max Activating Token Index: 1003

Text #17

Max Range: 0.3834. Min Range: -0.3834

Max Act: 0.2598. Min Act: -0.0000

Data Index: 785395 (The Pile)

Max Activating Token Index: 750

Text #18

Max Range: 0.3834. Min Range: -0.3834

Max Act: 0.3129. Min Act: -0.0000

Data Index: 1114444 (The Pile)

Max Activating Token Index: 189

Text #19

Max Range: 0.3834. Min Range: -0.3834

Max Act: 0.2610. Min Act: -0.0000

Data Index: 1368493 (The Pile)

Max Activating Token Index: 825