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

Dataset: The Pile

Neuron 616 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: 0.4963. Min Range: -0.4963

Max Act: 0.4805. Min Act: -0.0000

Data Index: 1426231 (The Pile)

Max Activating Token Index: 587

Text #1

Max Range: 0.4963. Min Range: -0.4963

Max Act: 0.4963. Min Act: -0.0000

Data Index: 225065 (The Pile)

Max Activating Token Index: 321

Text #2

Max Range: 0.4963. Min Range: -0.4963

Max Act: 0.4099. Min Act: -0.0000

Data Index: 1655100 (The Pile)

Max Activating Token Index: 1008

Text #3

Max Range: 0.4963. Min Range: -0.4963

Max Act: 0.4198. Min Act: -0.0000

Data Index: 1118950 (The Pile)

Max Activating Token Index: 675

Text #4

Max Range: 0.4963. Min Range: -0.4963

Max Act: 0.4143. Min Act: -0.0000

Data Index: 143543 (The Pile)

Max Activating Token Index: 259

Text #5

Max Range: 0.4963. Min Range: -0.4963

Max Act: 0.4004. Min Act: -0.0000

Data Index: 1258875 (The Pile)

Max Activating Token Index: 696

Text #6

Max Range: 0.4963. Min Range: -0.4963

Max Act: 0.4248. Min Act: -0.0000

Data Index: 1736927 (The Pile)

Max Activating Token Index: 171

Text #7

Max Range: 0.4963. Min Range: -0.4963

Max Act: 0.3914. Min Act: -0.0000

Data Index: 616599 (The Pile)

Max Activating Token Index: 50

Text #8

Max Range: 0.4963. Min Range: -0.4963

Max Act: 0.4179. Min Act: -0.0000

Data Index: 1533127 (The Pile)

Max Activating Token Index: 36

Text #9

Max Range: 0.4963. Min Range: -0.4963

Max Act: 0.3791. Min Act: -0.0000

Data Index: 1140589 (The Pile)

Max Activating Token Index: 737

Text #10

Max Range: 0.4963. Min Range: -0.4963

Max Act: 0.3926. Min Act: -0.0000

Data Index: 103387 (The Pile)

Max Activating Token Index: 128

Text #11

Max Range: 0.4963. Min Range: -0.4963

Max Act: 0.4024. Min Act: -0.0000

Data Index: 1541930 (The Pile)

Max Activating Token Index: 537

Text #12

Max Range: 0.4963. Min Range: -0.4963

Max Act: 0.3839. Min Act: -0.0000

Data Index: 1958391 (The Pile)

Max Activating Token Index: 883

Text #13

Max Range: 0.4963. Min Range: -0.4963

Max Act: 0.4150. Min Act: -0.0000

Data Index: 16926 (The Pile)

Max Activating Token Index: 29

Text #14

Max Range: 0.4963. Min Range: -0.4963

Max Act: 0.4218. Min Act: -0.0000

Data Index: 522167 (The Pile)

Max Activating Token Index: 375

Text #15

Max Range: 0.4963. Min Range: -0.4963

Max Act: 0.4070. Min Act: -0.0000

Data Index: 1857863 (The Pile)

Max Activating Token Index: 671

Text #16

Max Range: 0.4963. Min Range: -0.4963

Max Act: 0.3798. Min Act: -0.0000

Data Index: 1266972 (The Pile)

Max Activating Token Index: 498

Text #17

Max Range: 0.4963. Min Range: -0.4963

Max Act: 0.3922. Min Act: -0.0000

Data Index: 1797412 (The Pile)

Max Activating Token Index: 427

Text #18

Max Range: 0.4963. Min Range: -0.4963

Max Act: 0.3757. Min Act: -0.0000

Data Index: 1278599 (The Pile)

Max Activating Token Index: 724

Text #19

Max Range: 0.4963. Min Range: -0.4963

Max Act: 0.3763. Min Act: -0.0000

Data Index: 954685 (The Pile)

Max Activating Token Index: 499