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

Dataset: The Pile

Neuron 2850 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7700. Min Range: -0.7700

Max Act: 0.7440. Min Act: -0.0000

Data Index: 745246 (The Pile)

Max Activating Token Index: 9

Text #1

Max Range: 0.7700. Min Range: -0.7700

Max Act: 0.7700. Min Act: -0.0000

Data Index: 638445 (The Pile)

Max Activating Token Index: 41

Text #2

Max Range: 0.7700. Min Range: -0.7700

Max Act: 0.7434. Min Act: -0.0000

Data Index: 1677847 (The Pile)

Max Activating Token Index: 35

Text #3

Max Range: 0.7700. Min Range: -0.7700

Max Act: 0.7531. Min Act: -0.0000

Data Index: 1506549 (The Pile)

Max Activating Token Index: 534

Text #4

Max Range: 0.7700. Min Range: -0.7700

Max Act: 0.7230. Min Act: -0.0000

Data Index: 769529 (The Pile)

Max Activating Token Index: 692

Text #5

Max Range: 0.7700. Min Range: -0.7700

Max Act: 0.7177. Min Act: -0.0000

Data Index: 207695 (The Pile)

Max Activating Token Index: 695

Text #6

Max Range: 0.7700. Min Range: -0.7700

Max Act: 0.6855. Min Act: -0.0000

Data Index: 1910475 (The Pile)

Max Activating Token Index: 183

Text #7

Max Range: 0.7700. Min Range: -0.7700

Max Act: 0.6464. Min Act: -0.0000

Data Index: 1412914 (The Pile)

Max Activating Token Index: 126

Text #8

Max Range: 0.7700. Min Range: -0.7700

Max Act: 0.6183. Min Act: -0.0000

Data Index: 953043 (The Pile)

Max Activating Token Index: 456

Text #9

Max Range: 0.7700. Min Range: -0.7700

Max Act: 0.6313. Min Act: -0.0000

Data Index: 316086 (The Pile)

Max Activating Token Index: 33

Text #10

Max Range: 0.7700. Min Range: -0.7700

Max Act: 0.6122. Min Act: -0.0000

Data Index: 1521059 (The Pile)

Max Activating Token Index: 798

Text #11

Max Range: 0.7700. Min Range: -0.7700

Max Act: 0.6003. Min Act: -0.0000

Data Index: 1138786 (The Pile)

Max Activating Token Index: 52

Text #12

Max Range: 0.7700. Min Range: -0.7700

Max Act: 0.6187. Min Act: -0.0000

Data Index: 1495579 (The Pile)

Max Activating Token Index: 41

Text #13

Max Range: 0.7700. Min Range: -0.7700

Max Act: 0.6115. Min Act: -0.0000

Data Index: 1686878 (The Pile)

Max Activating Token Index: 573

Text #14

Max Range: 0.7700. Min Range: -0.7700

Max Act: 0.5989. Min Act: -0.0000

Data Index: 506241 (The Pile)

Max Activating Token Index: 236

Text #15

Max Range: 0.7700. Min Range: -0.7700

Max Act: 0.5897. Min Act: -0.0000

Data Index: 804676 (The Pile)

Max Activating Token Index: 500

Text #16

Max Range: 0.7700. Min Range: -0.7700

Max Act: 0.5731. Min Act: -0.0000

Data Index: 1128043 (The Pile)

Max Activating Token Index: 769

Text #17

Max Range: 0.7700. Min Range: -0.7700

Max Act: 0.5575. Min Act: -0.0000

Data Index: 1641046 (The Pile)

Max Activating Token Index: 118

Text #18

Max Range: 0.7700. Min Range: -0.7700

Max Act: 0.5932. Min Act: -0.0000

Data Index: 1624384 (The Pile)

Max Activating Token Index: 9

Text #19

Max Range: 0.7700. Min Range: -0.7700

Max Act: 0.5829. Min Act: -0.0000

Data Index: 270057 (The Pile)

Max Activating Token Index: 447