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

Dataset: The Pile

Neuron 4294 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2978. Min Range: -0.2978

Max Act: 0.2629. Min Act: -0.0000

Data Index: 1203796 (The Pile)

Max Activating Token Index: 953

Text #1

Max Range: 0.2978. Min Range: -0.2978

Max Act: 0.2969. Min Act: -0.0000

Data Index: 860999 (The Pile)

Max Activating Token Index: 882

Text #2

Max Range: 0.2978. Min Range: -0.2978

Max Act: 0.2733. Min Act: -0.0000

Data Index: 120265 (The Pile)

Max Activating Token Index: 730

Text #3

Max Range: 0.2978. Min Range: -0.2978

Max Act: 0.2978. Min Act: -0.0000

Data Index: 1697190 (The Pile)

Max Activating Token Index: 667

Text #4

Max Range: 0.2978. Min Range: -0.2978

Max Act: 0.2593. Min Act: -0.0000

Data Index: 1100791 (The Pile)

Max Activating Token Index: 48

Text #5

Max Range: 0.2978. Min Range: -0.2978

Max Act: 0.2750. Min Act: -0.0000

Data Index: 128636 (The Pile)

Max Activating Token Index: 757

Text #6

Max Range: 0.2978. Min Range: -0.2978

Max Act: 0.2630. Min Act: -0.0000

Data Index: 623062 (The Pile)

Max Activating Token Index: 509

Text #7

Max Range: 0.2978. Min Range: -0.2978

Max Act: 0.2390. Min Act: -0.0000

Data Index: 1469669 (The Pile)

Max Activating Token Index: 606

Text #8

Max Range: 0.2978. Min Range: -0.2978

Max Act: 0.2553. Min Act: -0.0000

Data Index: 1991377 (The Pile)

Max Activating Token Index: 115

Text #9

Max Range: 0.2978. Min Range: -0.2978

Max Act: 0.2541. Min Act: -0.0000

Data Index: 1029152 (The Pile)

Max Activating Token Index: 86

Text #10

Max Range: 0.2978. Min Range: -0.2978

Max Act: 0.2357. Min Act: -0.0000

Data Index: 1030570 (The Pile)

Max Activating Token Index: 306

Text #11

Max Range: 0.2978. Min Range: -0.2978

Max Act: 0.2175. Min Act: -0.0000

Data Index: 1957535 (The Pile)

Max Activating Token Index: 839

Text #12

Max Range: 0.2978. Min Range: -0.2978

Max Act: 0.2576. Min Act: -0.0000

Data Index: 102602 (The Pile)

Max Activating Token Index: 367

Text #13

Max Range: 0.2978. Min Range: -0.2978

Max Act: 0.2399. Min Act: -0.0000

Data Index: 338049 (The Pile)

Max Activating Token Index: 919

Text #14

Max Range: 0.2978. Min Range: -0.2978

Max Act: 0.2573. Min Act: -0.0000

Data Index: 1553695 (The Pile)

Max Activating Token Index: 67

Text #15

Max Range: 0.2978. Min Range: -0.2978

Max Act: 0.2133. Min Act: -0.0000

Data Index: 1867361 (The Pile)

Max Activating Token Index: 726

Text #16

Max Range: 0.2978. Min Range: -0.2978

Max Act: 0.2314. Min Act: -0.0000

Data Index: 220783 (The Pile)

Max Activating Token Index: 1021

Text #17

Max Range: 0.2978. Min Range: -0.2978

Max Act: 0.2227. Min Act: -0.0000

Data Index: 828789 (The Pile)

Max Activating Token Index: 944

Text #18

Max Range: 0.2978. Min Range: -0.2978

Max Act: 0.2166. Min Act: -0.0000

Data Index: 340298 (The Pile)

Max Activating Token Index: 882

Text #19

Max Range: 0.2978. Min Range: -0.2978

Max Act: 0.2155. Min Act: -0.0000

Data Index: 184832 (The Pile)

Max Activating Token Index: 688