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

Dataset: The Pile

Neuron 3697 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7935. Min Range: -0.7935

Max Act: 0.7935. Min Act: -0.0000

Data Index: 955364 (The Pile)

Max Activating Token Index: 989

Text #1

Max Range: 0.7935. Min Range: -0.7935

Max Act: 0.6791. Min Act: -0.0000

Data Index: 747210 (The Pile)

Max Activating Token Index: 177

Text #2

Max Range: 0.7935. Min Range: -0.7935

Max Act: 0.6064. Min Act: -0.0000

Data Index: 716299 (The Pile)

Max Activating Token Index: 875

Text #3

Max Range: 0.7935. Min Range: -0.7935

Max Act: 0.6117. Min Act: -0.0000

Data Index: 1385741 (The Pile)

Max Activating Token Index: 357

Text #4

Max Range: 0.7935. Min Range: -0.7935

Max Act: 0.5755. Min Act: -0.0000

Data Index: 104517 (The Pile)

Max Activating Token Index: 142

Text #5

Max Range: 0.7935. Min Range: -0.7935

Max Act: 0.5816. Min Act: -0.0000

Data Index: 1825289 (The Pile)

Max Activating Token Index: 127

Text #6

Max Range: 0.7935. Min Range: -0.7935

Max Act: 0.5467. Min Act: -0.0000

Data Index: 1865769 (The Pile)

Max Activating Token Index: 290

Text #7

Max Range: 0.7935. Min Range: -0.7935

Max Act: 0.5556. Min Act: -0.0000

Data Index: 743210 (The Pile)

Max Activating Token Index: 192

Text #8

Max Range: 0.7935. Min Range: -0.7935

Max Act: 0.5178. Min Act: -0.0000

Data Index: 23625 (The Pile)

Max Activating Token Index: 184

Text #9

Max Range: 0.7935. Min Range: -0.7935

Max Act: 0.5109. Min Act: -0.0000

Data Index: 1905411 (The Pile)

Max Activating Token Index: 318

Text #10

Max Range: 0.7935. Min Range: -0.7935

Max Act: 0.5492. Min Act: -0.0000

Data Index: 1637310 (The Pile)

Max Activating Token Index: 879

Text #11

Max Range: 0.7935. Min Range: -0.7935

Max Act: 0.4902. Min Act: -0.0000

Data Index: 502638 (The Pile)

Max Activating Token Index: 910

Text #12

Max Range: 0.7935. Min Range: -0.7935

Max Act: 0.5089. Min Act: -0.0000

Data Index: 545838 (The Pile)

Max Activating Token Index: 436

Text #13

Max Range: 0.7935. Min Range: -0.7935

Max Act: 0.4861. Min Act: -0.0000

Data Index: 439107 (The Pile)

Max Activating Token Index: 852

Text #14

Max Range: 0.7935. Min Range: -0.7935

Max Act: 0.4796. Min Act: -0.0000

Data Index: 1930254 (The Pile)

Max Activating Token Index: 512

Text #15

Max Range: 0.7935. Min Range: -0.7935

Max Act: 0.4992. Min Act: -0.0000

Data Index: 857622 (The Pile)

Max Activating Token Index: 239

Text #16

Max Range: 0.7935. Min Range: -0.7935

Max Act: 0.4856. Min Act: -0.0000

Data Index: 1343224 (The Pile)

Max Activating Token Index: 481

Text #17

Max Range: 0.7935. Min Range: -0.7935

Max Act: 0.4716. Min Act: -0.0000

Data Index: 1336404 (The Pile)

Max Activating Token Index: 251

Text #18

Max Range: 0.7935. Min Range: -0.7935

Max Act: 0.4854. Min Act: -0.0000

Data Index: 1101388 (The Pile)

Max Activating Token Index: 350

Text #19

Max Range: 0.7935. Min Range: -0.7935

Max Act: 0.4388. Min Act: -0.0000

Data Index: 1963445 (The Pile)

Max Activating Token Index: 285