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

Dataset: The Pile

Neuron 1551 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.7947. Min Act: -0.0000

Data Index: 1607673 (The Pile)

Max Activating Token Index: 8

Text #1

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.7395. Min Act: -0.0000

Data Index: 396199 (The Pile)

Max Activating Token Index: 643

Text #2

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.6864. Min Act: -0.0000

Data Index: 149648 (The Pile)

Max Activating Token Index: 764

Text #3

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.6536. Min Act: -0.0000

Data Index: 1065406 (The Pile)

Max Activating Token Index: 760

Text #4

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.6636. Min Act: -0.0000

Data Index: 1571228 (The Pile)

Max Activating Token Index: 928

Text #5

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.5969. Min Act: -0.0000

Data Index: 1600862 (The Pile)

Max Activating Token Index: 837

Text #6

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.5512. Min Act: -0.0000

Data Index: 1362251 (The Pile)

Max Activating Token Index: 698

Text #7

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.6092. Min Act: -0.0000

Data Index: 922695 (The Pile)

Max Activating Token Index: 489

Text #8

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.6539. Min Act: -0.0000

Data Index: 1302574 (The Pile)

Max Activating Token Index: 893

Text #9

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.6233. Min Act: -0.0000

Data Index: 1930458 (The Pile)

Max Activating Token Index: 909

Text #10

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.6336. Min Act: -0.0000

Data Index: 1575183 (The Pile)

Max Activating Token Index: 209

Text #11

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.5889. Min Act: -0.0000

Data Index: 1123526 (The Pile)

Max Activating Token Index: 987

Text #12

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.6042. Min Act: -0.0000

Data Index: 1650477 (The Pile)

Max Activating Token Index: 275

Text #13

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.5965. Min Act: -0.0000

Data Index: 1466008 (The Pile)

Max Activating Token Index: 773

Text #14

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.6018. Min Act: -0.0000

Data Index: 465078 (The Pile)

Max Activating Token Index: 1004

Text #15

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.5875. Min Act: -0.0000

Data Index: 362774 (The Pile)

Max Activating Token Index: 789

Text #16

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.6076. Min Act: -0.0000

Data Index: 1732980 (The Pile)

Max Activating Token Index: 720

Text #17

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.5777. Min Act: -0.0000

Data Index: 31573 (The Pile)

Max Activating Token Index: 497

Text #18

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.5340. Min Act: -0.0000

Data Index: 12866 (The Pile)

Max Activating Token Index: 954

Text #19

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.5323. Min Act: -0.0000

Data Index: 129972 (The Pile)

Max Activating Token Index: 78