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

Dataset: The Pile

Neuron 1351 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: 3.5333. Min Range: -3.5333

Max Act: 3.4757. Min Act: -0.0000

Data Index: 1528067 (The Pile)

Max Activating Token Index: 801

Text #1

Max Range: 3.5333. Min Range: -3.5333

Max Act: 3.4940. Min Act: -0.0000

Data Index: 1352489 (The Pile)

Max Activating Token Index: 137

Text #2

Max Range: 3.5333. Min Range: -3.5333

Max Act: 3.5333. Min Act: -0.0000

Data Index: 142158 (The Pile)

Max Activating Token Index: 851

Text #3

Max Range: 3.5333. Min Range: -3.5333

Max Act: 3.1982. Min Act: -0.0000

Data Index: 1321140 (The Pile)

Max Activating Token Index: 101

Text #4

Max Range: 3.5333. Min Range: -3.5333

Max Act: 3.0512. Min Act: -0.0000

Data Index: 859625 (The Pile)

Max Activating Token Index: 385

Text #5

Max Range: 3.5333. Min Range: -3.5333

Max Act: 3.0935. Min Act: -0.0000

Data Index: 1987413 (The Pile)

Max Activating Token Index: 78

Text #6

Max Range: 3.5333. Min Range: -3.5333

Max Act: 3.1009. Min Act: -0.0000

Data Index: 25861 (The Pile)

Max Activating Token Index: 534

Text #7

Max Range: 3.5333. Min Range: -3.5333

Max Act: 2.9069. Min Act: -0.0000

Data Index: 896346 (The Pile)

Max Activating Token Index: 150

Text #8

Max Range: 3.5333. Min Range: -3.5333

Max Act: 2.8865. Min Act: -0.0000

Data Index: 126926 (The Pile)

Max Activating Token Index: 945

Text #9

Max Range: 3.5333. Min Range: -3.5333

Max Act: 2.8850. Min Act: -0.0000

Data Index: 1086409 (The Pile)

Max Activating Token Index: 959

Text #10

Max Range: 3.5333. Min Range: -3.5333

Max Act: 2.4435. Min Act: -0.0000

Data Index: 1644998 (The Pile)

Max Activating Token Index: 151

Text #11

Max Range: 3.5333. Min Range: -3.5333

Max Act: 2.7871. Min Act: -0.0000

Data Index: 483265 (The Pile)

Max Activating Token Index: 153

Text #12

Max Range: 3.5333. Min Range: -3.5333

Max Act: 3.0557. Min Act: -0.0000

Data Index: 1658898 (The Pile)

Max Activating Token Index: 221

Text #13

Max Range: 3.5333. Min Range: -3.5333

Max Act: 2.7717. Min Act: -0.0000

Data Index: 1033965 (The Pile)

Max Activating Token Index: 27

Text #14

Max Range: 3.5333. Min Range: -3.5333

Max Act: 2.9020. Min Act: -0.0000

Data Index: 1984039 (The Pile)

Max Activating Token Index: 54

Text #15

Max Range: 3.5333. Min Range: -3.5333

Max Act: 2.9935. Min Act: -0.0000

Data Index: 1859155 (The Pile)

Max Activating Token Index: 428

Text #16

Max Range: 3.5333. Min Range: -3.5333

Max Act: 2.3995. Min Act: -0.0000

Data Index: 917603 (The Pile)

Max Activating Token Index: 86

Text #17

Max Range: 3.5333. Min Range: -3.5333

Max Act: 2.7180. Min Act: -0.0000

Data Index: 991692 (The Pile)

Max Activating Token Index: 188

Text #18

Max Range: 3.5333. Min Range: -3.5333

Max Act: 2.6836. Min Act: -0.0000

Data Index: 1027147 (The Pile)

Max Activating Token Index: 186

Text #19

Max Range: 3.5333. Min Range: -3.5333

Max Act: 2.6837. Min Act: -0.0000

Data Index: 1753702 (The Pile)

Max Activating Token Index: 93