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

Dataset: The Pile

Neuron 4727 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: 1.0146. Min Range: -1.0146

Max Act: 1.0070. Min Act: -0.0000

Data Index: 1613963 (The Pile)

Max Activating Token Index: 692

Text #1

Max Range: 1.0146. Min Range: -1.0146

Max Act: 0.9681. Min Act: 0.0000

Data Index: 388614 (The Pile)

Max Activating Token Index: 25

Text #2

Max Range: 1.0146. Min Range: -1.0146

Max Act: 1.0092. Min Act: -0.0000

Data Index: 380169 (The Pile)

Max Activating Token Index: 856

Text #3

Max Range: 1.0146. Min Range: -1.0146

Max Act: 1.0061. Min Act: -0.0000

Data Index: 635143 (The Pile)

Max Activating Token Index: 981

Text #4

Max Range: 1.0146. Min Range: -1.0146

Max Act: 1.0146. Min Act: -0.0000

Data Index: 175702 (The Pile)

Max Activating Token Index: 538

Text #5

Max Range: 1.0146. Min Range: -1.0146

Max Act: 0.9261. Min Act: -0.0000

Data Index: 550392 (The Pile)

Max Activating Token Index: 386

Text #6

Max Range: 1.0146. Min Range: -1.0146

Max Act: 0.8967. Min Act: -0.0000

Data Index: 710872 (The Pile)

Max Activating Token Index: 738

Text #7

Max Range: 1.0146. Min Range: -1.0146

Max Act: 0.8844. Min Act: -0.0000

Data Index: 1391793 (The Pile)

Max Activating Token Index: 193

Text #8

Max Range: 1.0146. Min Range: -1.0146

Max Act: 0.8337. Min Act: -0.0000

Data Index: 183129 (The Pile)

Max Activating Token Index: 955

Text #9

Max Range: 1.0146. Min Range: -1.0146

Max Act: 0.8590. Min Act: -0.0000

Data Index: 945846 (The Pile)

Max Activating Token Index: 196

Text #10

Max Range: 1.0146. Min Range: -1.0146

Max Act: 0.8379. Min Act: -0.0000

Data Index: 1839811 (The Pile)

Max Activating Token Index: 196

Text #11

Max Range: 1.0146. Min Range: -1.0146

Max Act: 0.7868. Min Act: -0.0000

Data Index: 1699134 (The Pile)

Max Activating Token Index: 152

Text #12

Max Range: 1.0146. Min Range: -1.0146

Max Act: 0.7937. Min Act: -0.0000

Data Index: 890075 (The Pile)

Max Activating Token Index: 56

Text #13

Max Range: 1.0146. Min Range: -1.0146

Max Act: 0.8072. Min Act: -0.0000

Data Index: 315372 (The Pile)

Max Activating Token Index: 151

Text #14

Max Range: 1.0146. Min Range: -1.0146

Max Act: 0.7799. Min Act: -0.0000

Data Index: 1687475 (The Pile)

Max Activating Token Index: 800

Text #15

Max Range: 1.0146. Min Range: -1.0146

Max Act: 0.7204. Min Act: -0.0000

Data Index: 263493 (The Pile)

Max Activating Token Index: 905

Text #16

Max Range: 1.0146. Min Range: -1.0146

Max Act: 0.7607. Min Act: -0.0000

Data Index: 304216 (The Pile)

Max Activating Token Index: 964

Text #17

Max Range: 1.0146. Min Range: -1.0146

Max Act: 0.7274. Min Act: 0.0000

Data Index: 55322 (The Pile)

Max Activating Token Index: 159

Text #18

Max Range: 1.0146. Min Range: -1.0146

Max Act: 0.7243. Min Act: -0.0000

Data Index: 565459 (The Pile)

Max Activating Token Index: 513

Text #19

Max Range: 1.0146. Min Range: -1.0146

Max Act: 0.6928. Min Act: -0.0000

Data Index: 21648 (The Pile)

Max Activating Token Index: 851