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

Dataset: The Pile

Neuron 2251 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: 5.3454. Min Range: -5.3454

Max Act: 5.3454. Min Act: -0.0000

Data Index: 1146141 (The Pile)

Max Activating Token Index: 723

Text #1

Max Range: 5.3454. Min Range: -5.3454

Max Act: 5.1172. Min Act: -0.0000

Data Index: 1075863 (The Pile)

Max Activating Token Index: 209

Text #2

Max Range: 5.3454. Min Range: -5.3454

Max Act: 4.7323. Min Act: -0.0000

Data Index: 204747 (The Pile)

Max Activating Token Index: 64

Text #3

Max Range: 5.3454. Min Range: -5.3454

Max Act: 4.6752. Min Act: -0.0000

Data Index: 1201424 (The Pile)

Max Activating Token Index: 131

Text #4

Max Range: 5.3454. Min Range: -5.3454

Max Act: 3.8832. Min Act: -0.0000

Data Index: 1636088 (The Pile)

Max Activating Token Index: 361

Text #5

Max Range: 5.3454. Min Range: -5.3454

Max Act: 4.2926. Min Act: -0.0000

Data Index: 1597831 (The Pile)

Max Activating Token Index: 525

Text #6

Max Range: 5.3454. Min Range: -5.3454

Max Act: 4.0148. Min Act: -0.0000

Data Index: 1265228 (The Pile)

Max Activating Token Index: 494

Text #7

Max Range: 5.3454. Min Range: -5.3454

Max Act: 4.2072. Min Act: -0.0000

Data Index: 193370 (The Pile)

Max Activating Token Index: 990

Text #8

Max Range: 5.3454. Min Range: -5.3454

Max Act: 4.1520. Min Act: -0.0000

Data Index: 1536444 (The Pile)

Max Activating Token Index: 870

Text #9

Max Range: 5.3454. Min Range: -5.3454

Max Act: 3.7997. Min Act: -0.0000

Data Index: 1640228 (The Pile)

Max Activating Token Index: 628

Text #10

Max Range: 5.3454. Min Range: -5.3454

Max Act: 3.7997. Min Act: -0.0000

Data Index: 1840409 (The Pile)

Max Activating Token Index: 167

Text #11

Max Range: 5.3454. Min Range: -5.3454

Max Act: 3.8538. Min Act: -0.0000

Data Index: 76789 (The Pile)

Max Activating Token Index: 225

Text #12

Max Range: 5.3454. Min Range: -5.3454

Max Act: 3.4078. Min Act: -0.0000

Data Index: 1686591 (The Pile)

Max Activating Token Index: 265

Text #13

Max Range: 5.3454. Min Range: -5.3454

Max Act: 3.6732. Min Act: -0.0000

Data Index: 989329 (The Pile)

Max Activating Token Index: 380

Text #14

Max Range: 5.3454. Min Range: -5.3454

Max Act: 3.9421. Min Act: -0.0000

Data Index: 1203084 (The Pile)

Max Activating Token Index: 904

Text #15

Max Range: 5.3454. Min Range: -5.3454

Max Act: 3.5664. Min Act: -0.0000

Data Index: 432173 (The Pile)

Max Activating Token Index: 494

Text #16

Max Range: 5.3454. Min Range: -5.3454

Max Act: 3.2860. Min Act: -0.0000

Data Index: 1990345 (The Pile)

Max Activating Token Index: 443

Text #17

Max Range: 5.3454. Min Range: -5.3454

Max Act: 3.1622. Min Act: -0.0000

Data Index: 1154549 (The Pile)

Max Activating Token Index: 837

Text #18

Max Range: 5.3454. Min Range: -5.3454

Max Act: 3.3947. Min Act: -0.0000

Data Index: 20475 (The Pile)

Max Activating Token Index: 700

Text #19

Max Range: 5.3454. Min Range: -5.3454

Max Act: 3.4123. Min Act: -0.0000

Data Index: 1223182 (The Pile)

Max Activating Token Index: 449