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

Dataset: The Pile

Neuron 1281 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0217. Min Range: -1.0217

Max Act: 1.0217. Min Act: -0.0000

Data Index: 1289335 (The Pile)

Max Activating Token Index: 794

Text #1

Max Range: 1.0217. Min Range: -1.0217

Max Act: 0.9246. Min Act: -0.0000

Data Index: 174010 (The Pile)

Max Activating Token Index: 614

Text #2

Max Range: 1.0217. Min Range: -1.0217

Max Act: 0.9041. Min Act: -0.0000

Data Index: 1194440 (The Pile)

Max Activating Token Index: 906

Text #3

Max Range: 1.0217. Min Range: -1.0217

Max Act: 0.8944. Min Act: -0.0000

Data Index: 1569387 (The Pile)

Max Activating Token Index: 695

Text #4

Max Range: 1.0217. Min Range: -1.0217

Max Act: 0.8449. Min Act: -0.0000

Data Index: 203742 (The Pile)

Max Activating Token Index: 870

Text #5

Max Range: 1.0217. Min Range: -1.0217

Max Act: 0.8602. Min Act: -0.0000

Data Index: 1669054 (The Pile)

Max Activating Token Index: 386

Text #6

Max Range: 1.0217. Min Range: -1.0217

Max Act: 0.8633. Min Act: -0.0000

Data Index: 229481 (The Pile)

Max Activating Token Index: 391

Text #7

Max Range: 1.0217. Min Range: -1.0217

Max Act: 0.8821. Min Act: -0.0000

Data Index: 1371581 (The Pile)

Max Activating Token Index: 140

Text #8

Max Range: 1.0217. Min Range: -1.0217

Max Act: 0.8787. Min Act: -0.0000

Data Index: 85738 (The Pile)

Max Activating Token Index: 327

Text #9

Max Range: 1.0217. Min Range: -1.0217

Max Act: 0.8753. Min Act: -0.0000

Data Index: 1030004 (The Pile)

Max Activating Token Index: 205

Text #10

Max Range: 1.0217. Min Range: -1.0217

Max Act: 0.8430. Min Act: -0.0000

Data Index: 1517611 (The Pile)

Max Activating Token Index: 453

Text #11

Max Range: 1.0217. Min Range: -1.0217

Max Act: 0.8424. Min Act: -0.0000

Data Index: 1197584 (The Pile)

Max Activating Token Index: 293

Text #12

Max Range: 1.0217. Min Range: -1.0217

Max Act: 0.7830. Min Act: -0.0000

Data Index: 197526 (The Pile)

Max Activating Token Index: 321

Text #13

Max Range: 1.0217. Min Range: -1.0217

Max Act: 0.8141. Min Act: -0.0000

Data Index: 1904295 (The Pile)

Max Activating Token Index: 317

Text #14

Max Range: 1.0217. Min Range: -1.0217

Max Act: 0.8081. Min Act: -0.0000

Data Index: 540011 (The Pile)

Max Activating Token Index: 219

Text #15

Max Range: 1.0217. Min Range: -1.0217

Max Act: 0.8055. Min Act: -0.0000

Data Index: 430181 (The Pile)

Max Activating Token Index: 107

Text #16

Max Range: 1.0217. Min Range: -1.0217

Max Act: 0.7753. Min Act: -0.0000

Data Index: 271740 (The Pile)

Max Activating Token Index: 178

Text #17

Max Range: 1.0217. Min Range: -1.0217

Max Act: 0.8454. Min Act: -0.0000

Data Index: 1277188 (The Pile)

Max Activating Token Index: 704

Text #18

Max Range: 1.0217. Min Range: -1.0217

Max Act: 0.7763. Min Act: -0.0000

Data Index: 1683068 (The Pile)

Max Activating Token Index: 447

Text #19

Max Range: 1.0217. Min Range: -1.0217

Max Act: 0.7476. Min Act: -0.0000

Data Index: 1293320 (The Pile)

Max Activating Token Index: 290