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

Dataset: The Pile

Neuron 2977 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0820. Min Range: -1.0820

Max Act: 1.0820. Min Act: -0.0000

Data Index: 1981039 (The Pile)

Max Activating Token Index: 466

Text #1

Max Range: 1.0820. Min Range: -1.0820

Max Act: 0.9438. Min Act: -0.0000

Data Index: 707581 (The Pile)

Max Activating Token Index: 12

Text #2

Max Range: 1.0820. Min Range: -1.0820

Max Act: 0.9321. Min Act: -0.0000

Data Index: 975446 (The Pile)

Max Activating Token Index: 270

Text #3

Max Range: 1.0820. Min Range: -1.0820

Max Act: 0.9004. Min Act: -0.0000

Data Index: 884522 (The Pile)

Max Activating Token Index: 903

Text #4

Max Range: 1.0820. Min Range: -1.0820

Max Act: 0.6498. Min Act: -0.0000

Data Index: 1960361 (The Pile)

Max Activating Token Index: 746

Text #5

Max Range: 1.0820. Min Range: -1.0820

Max Act: 0.8395. Min Act: -0.0001

Data Index: 1959211 (The Pile)

Max Activating Token Index: 228

Text #6

Max Range: 1.0820. Min Range: -1.0820

Max Act: 0.7935. Min Act: -0.0001

Data Index: 1282066 (The Pile)

Max Activating Token Index: 165

Text #7

Max Range: 1.0820. Min Range: -1.0820

Max Act: 0.7202. Min Act: -0.0000

Data Index: 1938011 (The Pile)

Max Activating Token Index: 613

Text #8

Max Range: 1.0820. Min Range: -1.0820

Max Act: 0.6649. Min Act: -0.0000

Data Index: 1014095 (The Pile)

Max Activating Token Index: 706

Text #9

Max Range: 1.0820. Min Range: -1.0820

Max Act: 0.7370. Min Act: -0.0001

Data Index: 1241693 (The Pile)

Max Activating Token Index: 218

Text #10

Max Range: 1.0820. Min Range: -1.0820

Max Act: 0.7349. Min Act: -0.0000

Data Index: 1474821 (The Pile)

Max Activating Token Index: 810

Text #11

Max Range: 1.0820. Min Range: -1.0820

Max Act: 0.7299. Min Act: -0.0000

Data Index: 972253 (The Pile)

Max Activating Token Index: 264

Text #12

Max Range: 1.0820. Min Range: -1.0820

Max Act: 0.7320. Min Act: 0.0000

Data Index: 1998432 (The Pile)

Max Activating Token Index: 668

Text #13

Max Range: 1.0820. Min Range: -1.0820

Max Act: 0.6507. Min Act: -0.0000

Data Index: 1032154 (The Pile)

Max Activating Token Index: 487

Text #14

Max Range: 1.0820. Min Range: -1.0820

Max Act: 0.6973. Min Act: -0.0000

Data Index: 1865580 (The Pile)

Max Activating Token Index: 216

Text #15

Max Range: 1.0820. Min Range: -1.0820

Max Act: 0.6747. Min Act: -0.0000

Data Index: 639306 (The Pile)

Max Activating Token Index: 172

Text #16

Max Range: 1.0820. Min Range: -1.0820

Max Act: 0.6696. Min Act: -0.0000

Data Index: 467213 (The Pile)

Max Activating Token Index: 580

Text #17

Max Range: 1.0820. Min Range: -1.0820

Max Act: 0.6048. Min Act: -0.0000

Data Index: 449996 (The Pile)

Max Activating Token Index: 820

Text #18

Max Range: 1.0820. Min Range: -1.0820

Max Act: 0.6592. Min Act: 0.0000

Data Index: 126366 (The Pile)

Max Activating Token Index: 506

Text #19

Max Range: 1.0820. Min Range: -1.0820

Max Act: 0.6886. Min Act: -0.0000

Data Index: 956677 (The Pile)

Max Activating Token Index: 44