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

Dataset: The Pile

Neuron 449 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.2926. Min Range: -3.2926

Max Act: 3.2926. Min Act: -0.0000

Data Index: 1591606 (The Pile)

Max Activating Token Index: 823

Text #1

Max Range: 3.2926. Min Range: -3.2926

Max Act: 2.1661. Min Act: -0.0000

Data Index: 1138510 (The Pile)

Max Activating Token Index: 300

Text #2

Max Range: 3.2926. Min Range: -3.2926

Max Act: 2.0982. Min Act: -0.0000

Data Index: 1942357 (The Pile)

Max Activating Token Index: 205

Text #3

Max Range: 3.2926. Min Range: -3.2926

Max Act: 2.1445. Min Act: 0.0000

Data Index: 1907231 (The Pile)

Max Activating Token Index: 442

Text #4

Max Range: 3.2926. Min Range: -3.2926

Max Act: 2.0574. Min Act: 0.0000

Data Index: 197497 (The Pile)

Max Activating Token Index: 652

Text #5

Max Range: 3.2926. Min Range: -3.2926

Max Act: 1.9572. Min Act: -0.0000

Data Index: 1464140 (The Pile)

Max Activating Token Index: 89

Text #6

Max Range: 3.2926. Min Range: -3.2926

Max Act: 2.1405. Min Act: 0.0000

Data Index: 976050 (The Pile)

Max Activating Token Index: 86

Text #7

Max Range: 3.2926. Min Range: -3.2926

Max Act: 1.7840. Min Act: -0.0000

Data Index: 1627790 (The Pile)

Max Activating Token Index: 185

Text #8

Max Range: 3.2926. Min Range: -3.2926

Max Act: 1.7096. Min Act: -0.0000

Data Index: 360451 (The Pile)

Max Activating Token Index: 332

Text #9

Max Range: 3.2926. Min Range: -3.2926

Max Act: 1.7681. Min Act: -0.0000

Data Index: 1483731 (The Pile)

Max Activating Token Index: 478

Text #10

Max Range: 3.2926. Min Range: -3.2926

Max Act: 1.6472. Min Act: -0.0000

Data Index: 1851015 (The Pile)

Max Activating Token Index: 592

Text #11

Max Range: 3.2926. Min Range: -3.2926

Max Act: 1.6594. Min Act: -0.0000

Data Index: 1189317 (The Pile)

Max Activating Token Index: 780

Text #12

Max Range: 3.2926. Min Range: -3.2926

Max Act: 1.7959. Min Act: -0.0000

Data Index: 1458334 (The Pile)

Max Activating Token Index: 904

Text #13

Max Range: 3.2926. Min Range: -3.2926

Max Act: 1.5883. Min Act: -0.0000

Data Index: 101581 (The Pile)

Max Activating Token Index: 107

Text #14

Max Range: 3.2926. Min Range: -3.2926

Max Act: 1.6469. Min Act: -0.0000

Data Index: 1642852 (The Pile)

Max Activating Token Index: 451

Text #15

Max Range: 3.2926. Min Range: -3.2926

Max Act: 1.6104. Min Act: -0.0000

Data Index: 639980 (The Pile)

Max Activating Token Index: 275

Text #16

Max Range: 3.2926. Min Range: -3.2926

Max Act: 1.6299. Min Act: -0.0000

Data Index: 988570 (The Pile)

Max Activating Token Index: 45

Text #17

Max Range: 3.2926. Min Range: -3.2926

Max Act: 1.6884. Min Act: -0.0000

Data Index: 598390 (The Pile)

Max Activating Token Index: 520

Text #18

Max Range: 3.2926. Min Range: -3.2926

Max Act: 1.6030. Min Act: -0.0000

Data Index: 1700977 (The Pile)

Max Activating Token Index: 414

Text #19

Max Range: 3.2926. Min Range: -3.2926

Max Act: 1.5050. Min Act: -0.0000

Data Index: 238917 (The Pile)

Max Activating Token Index: 355