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

Dataset: The Pile

Neuron 2137 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: 0.9747. Min Range: -0.9747

Max Act: 0.9747. Min Act: -0.0000

Data Index: 286810 (The Pile)

Max Activating Token Index: 125

Text #1

Max Range: 0.9747. Min Range: -0.9747

Max Act: 0.8102. Min Act: -0.0000

Data Index: 987730 (The Pile)

Max Activating Token Index: 907

Text #2

Max Range: 0.9747. Min Range: -0.9747

Max Act: 0.8143. Min Act: -0.0000

Data Index: 172590 (The Pile)

Max Activating Token Index: 901

Text #3

Max Range: 0.9747. Min Range: -0.9747

Max Act: 0.8551. Min Act: -0.0000

Data Index: 290193 (The Pile)

Max Activating Token Index: 608

Text #4

Max Range: 0.9747. Min Range: -0.9747

Max Act: 0.6896. Min Act: -0.0000

Data Index: 1682055 (The Pile)

Max Activating Token Index: 565

Text #5

Max Range: 0.9747. Min Range: -0.9747

Max Act: 0.6801. Min Act: -0.0000

Data Index: 1426045 (The Pile)

Max Activating Token Index: 208

Text #6

Max Range: 0.9747. Min Range: -0.9747

Max Act: 0.7301. Min Act: -0.0000

Data Index: 79676 (The Pile)

Max Activating Token Index: 848

Text #7

Max Range: 0.9747. Min Range: -0.9747

Max Act: 0.7081. Min Act: -0.0000

Data Index: 1826077 (The Pile)

Max Activating Token Index: 896

Text #8

Max Range: 0.9747. Min Range: -0.9747

Max Act: 0.6810. Min Act: -0.0000

Data Index: 1971774 (The Pile)

Max Activating Token Index: 881

Text #9

Max Range: 0.9747. Min Range: -0.9747

Max Act: 0.6697. Min Act: -0.0000

Data Index: 436969 (The Pile)

Max Activating Token Index: 21

Text #10

Max Range: 0.9747. Min Range: -0.9747

Max Act: 0.6862. Min Act: -0.0000

Data Index: 919775 (The Pile)

Max Activating Token Index: 219

Text #11

Max Range: 0.9747. Min Range: -0.9747

Max Act: 0.7410. Min Act: -0.0000

Data Index: 375758 (The Pile)

Max Activating Token Index: 527

Text #12

Max Range: 0.9747. Min Range: -0.9747

Max Act: 0.7021. Min Act: -0.0000

Data Index: 147389 (The Pile)

Max Activating Token Index: 317

Text #13

Max Range: 0.9747. Min Range: -0.9747

Max Act: 0.6792. Min Act: -0.0000

Data Index: 1166809 (The Pile)

Max Activating Token Index: 77

Text #14

Max Range: 0.9747. Min Range: -0.9747

Max Act: 0.6481. Min Act: -0.0000

Data Index: 1151147 (The Pile)

Max Activating Token Index: 184

Text #15

Max Range: 0.9747. Min Range: -0.9747

Max Act: 0.6385. Min Act: -0.0000

Data Index: 1274139 (The Pile)

Max Activating Token Index: 139

Text #16

Max Range: 0.9747. Min Range: -0.9747

Max Act: 0.6261. Min Act: -0.0000

Data Index: 863803 (The Pile)

Max Activating Token Index: 234

Text #17

Max Range: 0.9747. Min Range: -0.9747

Max Act: 0.6573. Min Act: -0.0000

Data Index: 890793 (The Pile)

Max Activating Token Index: 339

Text #18

Max Range: 0.9747. Min Range: -0.9747

Max Act: 0.6572. Min Act: -0.0000

Data Index: 1175565 (The Pile)

Max Activating Token Index: 611

Text #19

Max Range: 0.9747. Min Range: -0.9747

Max Act: 0.6381. Min Act: -0.0000

Data Index: 1844317 (The Pile)

Max Activating Token Index: 869