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

Dataset: The Pile

Neuron 852 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4808. Min Range: -4.4808

Max Act: 4.4808. Min Act: -0.0000

Data Index: 58139 (The Pile)

Max Activating Token Index: 159

Text #1

Max Range: 4.4808. Min Range: -4.4808

Max Act: 4.3116. Min Act: -0.0000

Data Index: 1168835 (The Pile)

Max Activating Token Index: 33

Text #2

Max Range: 4.4808. Min Range: -4.4808

Max Act: 3.8765. Min Act: -0.0000

Data Index: 1237414 (The Pile)

Max Activating Token Index: 771

Text #3

Max Range: 4.4808. Min Range: -4.4808

Max Act: 3.9901. Min Act: -0.0000

Data Index: 1201219 (The Pile)

Max Activating Token Index: 321

Text #4

Max Range: 4.4808. Min Range: -4.4808

Max Act: 3.8114. Min Act: -0.0000

Data Index: 436134 (The Pile)

Max Activating Token Index: 728

Text #5

Max Range: 4.4808. Min Range: -4.4808

Max Act: 3.7221. Min Act: -0.0000

Data Index: 628968 (The Pile)

Max Activating Token Index: 685

Text #6

Max Range: 4.4808. Min Range: -4.4808

Max Act: 3.6446. Min Act: -0.0000

Data Index: 837129 (The Pile)

Max Activating Token Index: 497

Text #7

Max Range: 4.4808. Min Range: -4.4808

Max Act: 3.6057. Min Act: -0.0000

Data Index: 774689 (The Pile)

Max Activating Token Index: 625

Text #8

Max Range: 4.4808. Min Range: -4.4808

Max Act: 3.5944. Min Act: -0.0000

Data Index: 1058139 (The Pile)

Max Activating Token Index: 612

Text #9

Max Range: 4.4808. Min Range: -4.4808

Max Act: 3.5343. Min Act: -0.0000

Data Index: 1190506 (The Pile)

Max Activating Token Index: 584

Text #10

Max Range: 4.4808. Min Range: -4.4808

Max Act: 3.4778. Min Act: -0.0000

Data Index: 486148 (The Pile)

Max Activating Token Index: 46

Text #11

Max Range: 4.4808. Min Range: -4.4808

Max Act: 3.4715. Min Act: -0.0000

Data Index: 354686 (The Pile)

Max Activating Token Index: 938

Text #12

Max Range: 4.4808. Min Range: -4.4808

Max Act: 3.5791. Min Act: -0.0000

Data Index: 273277 (The Pile)

Max Activating Token Index: 78

Text #13

Max Range: 4.4808. Min Range: -4.4808

Max Act: 3.4313. Min Act: -0.0000

Data Index: 1279280 (The Pile)

Max Activating Token Index: 736

Text #14

Max Range: 4.4808. Min Range: -4.4808

Max Act: 3.4119. Min Act: -0.0000

Data Index: 1101864 (The Pile)

Max Activating Token Index: 513

Text #15

Max Range: 4.4808. Min Range: -4.4808

Max Act: 3.5691. Min Act: -0.0000

Data Index: 644963 (The Pile)

Max Activating Token Index: 236

Text #16

Max Range: 4.4808. Min Range: -4.4808

Max Act: 3.4113. Min Act: -0.0000

Data Index: 194128 (The Pile)

Max Activating Token Index: 467

Text #17

Max Range: 4.4808. Min Range: -4.4808

Max Act: 3.3434. Min Act: -0.0000

Data Index: 318547 (The Pile)

Max Activating Token Index: 851

Text #18

Max Range: 4.4808. Min Range: -4.4808

Max Act: 3.1665. Min Act: -0.0000

Data Index: 633178 (The Pile)

Max Activating Token Index: 404

Text #19

Max Range: 4.4808. Min Range: -4.4808

Max Act: 3.3039. Min Act: -0.0000

Data Index: 1647167 (The Pile)

Max Activating Token Index: 293