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

Dataset: The Pile

Neuron 4074 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1873. Min Range: -1.1873

Max Act: 1.1873. Min Act: -0.0000

Data Index: 683090 (The Pile)

Max Activating Token Index: 565

Text #1

Max Range: 1.1873. Min Range: -1.1873

Max Act: 1.1717. Min Act: -0.0000

Data Index: 1347212 (The Pile)

Max Activating Token Index: 308

Text #2

Max Range: 1.1873. Min Range: -1.1873

Max Act: 0.8875. Min Act: -0.0000

Data Index: 1805805 (The Pile)

Max Activating Token Index: 679

Text #3

Max Range: 1.1873. Min Range: -1.1873

Max Act: 0.7569. Min Act: -0.0000

Data Index: 1729294 (The Pile)

Max Activating Token Index: 556

Text #4

Max Range: 1.1873. Min Range: -1.1873

Max Act: 0.7307. Min Act: -0.0000

Data Index: 705260 (The Pile)

Max Activating Token Index: 483

Text #5

Max Range: 1.1873. Min Range: -1.1873

Max Act: 0.7120. Min Act: -0.0000

Data Index: 1178297 (The Pile)

Max Activating Token Index: 1016

Text #6

Max Range: 1.1873. Min Range: -1.1873

Max Act: 0.7197. Min Act: -0.0000

Data Index: 1461703 (The Pile)

Max Activating Token Index: 201

Text #7

Max Range: 1.1873. Min Range: -1.1873

Max Act: 0.7029. Min Act: -0.0000

Data Index: 1380895 (The Pile)

Max Activating Token Index: 203

Text #8

Max Range: 1.1873. Min Range: -1.1873

Max Act: 0.7122. Min Act: -0.0000

Data Index: 307160 (The Pile)

Max Activating Token Index: 745

Text #9

Max Range: 1.1873. Min Range: -1.1873

Max Act: 0.6593. Min Act: -0.0000

Data Index: 1705927 (The Pile)

Max Activating Token Index: 763

Text #10

Max Range: 1.1873. Min Range: -1.1873

Max Act: 0.6759. Min Act: -0.0000

Data Index: 1214528 (The Pile)

Max Activating Token Index: 845

Text #11

Max Range: 1.1873. Min Range: -1.1873

Max Act: 0.6711. Min Act: -0.0000

Data Index: 156482 (The Pile)

Max Activating Token Index: 216

Text #12

Max Range: 1.1873. Min Range: -1.1873

Max Act: 0.6418. Min Act: -0.0000

Data Index: 1091753 (The Pile)

Max Activating Token Index: 215

Text #13

Max Range: 1.1873. Min Range: -1.1873

Max Act: 0.6438. Min Act: -0.0000

Data Index: 1509608 (The Pile)

Max Activating Token Index: 629

Text #14

Max Range: 1.1873. Min Range: -1.1873

Max Act: 0.6658. Min Act: -0.0000

Data Index: 594901 (The Pile)

Max Activating Token Index: 35

Text #15

Max Range: 1.1873. Min Range: -1.1873

Max Act: 0.6136. Min Act: -0.0000

Data Index: 1603007 (The Pile)

Max Activating Token Index: 966

Text #16

Max Range: 1.1873. Min Range: -1.1873

Max Act: 0.6134. Min Act: -0.0000

Data Index: 1106768 (The Pile)

Max Activating Token Index: 185

Text #17

Max Range: 1.1873. Min Range: -1.1873

Max Act: 0.6573. Min Act: -0.0000

Data Index: 1840911 (The Pile)

Max Activating Token Index: 20

Text #18

Max Range: 1.1873. Min Range: -1.1873

Max Act: 0.6542. Min Act: 0.0000

Data Index: 1470097 (The Pile)

Max Activating Token Index: 27

Text #19

Max Range: 1.1873. Min Range: -1.1873

Max Act: 0.5761. Min Act: -0.0001

Data Index: 926056 (The Pile)

Max Activating Token Index: 386