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

Dataset: The Pile

Neuron 529 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: 0.8113. Min Range: -0.8113

Max Act: 0.7667. Min Act: -0.0000

Data Index: 135593 (The Pile)

Max Activating Token Index: 230

Text #1

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.8113. Min Act: -0.0000

Data Index: 1519251 (The Pile)

Max Activating Token Index: 465

Text #2

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.7209. Min Act: -0.0000

Data Index: 1034675 (The Pile)

Max Activating Token Index: 845

Text #3

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.7423. Min Act: -0.0000

Data Index: 69650 (The Pile)

Max Activating Token Index: 257

Text #4

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.7032. Min Act: -0.0000

Data Index: 350049 (The Pile)

Max Activating Token Index: 908

Text #5

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.6864. Min Act: -0.0000

Data Index: 1569067 (The Pile)

Max Activating Token Index: 851

Text #6

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.6721. Min Act: -0.0000

Data Index: 1827237 (The Pile)

Max Activating Token Index: 991

Text #7

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.6658. Min Act: -0.0000

Data Index: 795781 (The Pile)

Max Activating Token Index: 468

Text #8

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.6446. Min Act: -0.0000

Data Index: 523704 (The Pile)

Max Activating Token Index: 129

Text #9

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.6163. Min Act: -0.0000

Data Index: 188614 (The Pile)

Max Activating Token Index: 99

Text #10

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.6438. Min Act: -0.0000

Data Index: 1869890 (The Pile)

Max Activating Token Index: 771

Text #11

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.5638. Min Act: -0.0000

Data Index: 1223085 (The Pile)

Max Activating Token Index: 837

Text #12

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.5802. Min Act: -0.0000

Data Index: 979200 (The Pile)

Max Activating Token Index: 151

Text #13

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.5194. Min Act: -0.0000

Data Index: 1207940 (The Pile)

Max Activating Token Index: 205

Text #14

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.5858. Min Act: -0.0000

Data Index: 1980793 (The Pile)

Max Activating Token Index: 495

Text #15

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.5039. Min Act: -0.0000

Data Index: 1001282 (The Pile)

Max Activating Token Index: 662

Text #16

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.5762. Min Act: -0.0000

Data Index: 1123517 (The Pile)

Max Activating Token Index: 614

Text #17

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.5705. Min Act: -0.0000

Data Index: 138354 (The Pile)

Max Activating Token Index: 945

Text #18

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.5858. Min Act: -0.0000

Data Index: 1422924 (The Pile)

Max Activating Token Index: 376

Text #19

Max Range: 0.8113. Min Range: -0.8113

Max Act: 0.5296. Min Act: -0.0000

Data Index: 555797 (The Pile)

Max Activating Token Index: 553