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

Dataset: The Pile

Neuron 1186 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: 0.9840. Min Range: -0.9840

Max Act: 0.9840. Min Act: -0.0000

Data Index: 862090 (The Pile)

Max Activating Token Index: 183

Text #1

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.6904. Min Act: -0.0000

Data Index: 1582821 (The Pile)

Max Activating Token Index: 433

Text #2

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.7394. Min Act: -0.0000

Data Index: 1687120 (The Pile)

Max Activating Token Index: 135

Text #3

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.7169. Min Act: -0.0000

Data Index: 1429062 (The Pile)

Max Activating Token Index: 254

Text #4

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.6859. Min Act: -0.0000

Data Index: 820898 (The Pile)

Max Activating Token Index: 23

Text #5

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.6716. Min Act: -0.0000

Data Index: 1393523 (The Pile)

Max Activating Token Index: 918

Text #6

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.6348. Min Act: -0.0000

Data Index: 1794129 (The Pile)

Max Activating Token Index: 101

Text #7

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.6384. Min Act: -0.0000

Data Index: 90467 (The Pile)

Max Activating Token Index: 103

Text #8

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.6209. Min Act: -0.0000

Data Index: 1600133 (The Pile)

Max Activating Token Index: 552

Text #9

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.6137. Min Act: -0.0000

Data Index: 1010536 (The Pile)

Max Activating Token Index: 446

Text #10

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.6051. Min Act: -0.0000

Data Index: 910665 (The Pile)

Max Activating Token Index: 821

Text #11

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.4973. Min Act: -0.0000

Data Index: 900488 (The Pile)

Max Activating Token Index: 597

Text #12

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.5797. Min Act: -0.0000

Data Index: 839002 (The Pile)

Max Activating Token Index: 293

Text #13

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.5937. Min Act: -0.0000

Data Index: 423845 (The Pile)

Max Activating Token Index: 88

Text #14

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.5811. Min Act: -0.0000

Data Index: 1797237 (The Pile)

Max Activating Token Index: 883

Text #15

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.5578. Min Act: -0.0000

Data Index: 1914381 (The Pile)

Max Activating Token Index: 331

Text #16

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.5744. Min Act: -0.0000

Data Index: 1060410 (The Pile)

Max Activating Token Index: 957

Text #17

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.6015. Min Act: -0.0000

Data Index: 923710 (The Pile)

Max Activating Token Index: 45

Text #18

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.5440. Min Act: -0.0000

Data Index: 1126981 (The Pile)

Max Activating Token Index: 12

Text #19

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.5716. Min Act: -0.0000

Data Index: 205187 (The Pile)

Max Activating Token Index: 1000