Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3777 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.7377. Min Act: -0.0000

Data Index: 647329 (The Pile)

Max Activating Token Index: 304

Text #1

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.6826. Min Act: -0.0000

Data Index: 113617 (The Pile)

Max Activating Token Index: 390

Text #2

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.6352. Min Act: -0.0000

Data Index: 1767209 (The Pile)

Max Activating Token Index: 127

Text #3

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.6740. Min Act: -0.0000

Data Index: 162166 (The Pile)

Max Activating Token Index: 203

Text #4

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.5833. Min Act: -0.0000

Data Index: 960258 (The Pile)

Max Activating Token Index: 76

Text #5

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.5503. Min Act: -0.0000

Data Index: 1437044 (The Pile)

Max Activating Token Index: 233

Text #6

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.5251. Min Act: -0.0000

Data Index: 512791 (The Pile)

Max Activating Token Index: 538

Text #7

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.5339. Min Act: -0.0000

Data Index: 278140 (The Pile)

Max Activating Token Index: 639

Text #8

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.5461. Min Act: -0.0000

Data Index: 1542693 (The Pile)

Max Activating Token Index: 219

Text #9

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.4894. Min Act: -0.0000

Data Index: 598240 (The Pile)

Max Activating Token Index: 192

Text #10

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.5276. Min Act: -0.0000

Data Index: 1973954 (The Pile)

Max Activating Token Index: 828

Text #11

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.5119. Min Act: -0.0000

Data Index: 334062 (The Pile)

Max Activating Token Index: 285

Text #12

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.5032. Min Act: -0.0000

Data Index: 281070 (The Pile)

Max Activating Token Index: 470

Text #13

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.5021. Min Act: -0.0000

Data Index: 1756645 (The Pile)

Max Activating Token Index: 603

Text #14

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.4539. Min Act: -0.0000

Data Index: 1085337 (The Pile)

Max Activating Token Index: 832

Text #15

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.4674. Min Act: -0.0000

Data Index: 64765 (The Pile)

Max Activating Token Index: 104

Text #16

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.4768. Min Act: -0.0000

Data Index: 1984347 (The Pile)

Max Activating Token Index: 397

Text #17

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.4603. Min Act: -0.0000

Data Index: 473377 (The Pile)

Max Activating Token Index: 202

Text #18

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.4244. Min Act: -0.0000

Data Index: 1104278 (The Pile)

Max Activating Token Index: 709

Text #19

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.4696. Min Act: -0.0000

Data Index: 1979653 (The Pile)

Max Activating Token Index: 127