Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2082 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 0.6397. Min Range: -0.6397
Max Act: 0.5869. Min Act: 0.0002
Data Index: 454226 (The Pile)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6397. Min Range: -0.6397
Max Act: 0.6397. Min Act: 0.0002
Data Index: 1191065 (The Pile)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6397. Min Range: -0.6397
Max Act: 0.6107. Min Act: 0.0013
Data Index: 137848 (The Pile)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6397. Min Range: -0.6397
Max Act: 0.4834. Min Act: -0.0000
Data Index: 596331 (The Pile)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6397. Min Range: -0.6397
Max Act: 0.4628. Min Act: 0.0008
Data Index: 1132385 (The Pile)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6397. Min Range: -0.6397
Max Act: 0.5097. Min Act: 0.0002
Data Index: 1915517 (The Pile)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6397. Min Range: -0.6397
Max Act: 0.4665. Min Act: 0.0010
Data Index: 940327 (The Pile)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6397. Min Range: -0.6397
Max Act: 0.4498. Min Act: 0.0025
Data Index: 1227000 (The Pile)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6397. Min Range: -0.6397
Max Act: 0.4650. Min Act: 0.0005
Data Index: 1730488 (The Pile)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6397. Min Range: -0.6397
Max Act: 0.4146. Min Act: 0.0008
Data Index: 1825349 (The Pile)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6397. Min Range: -0.6397
Max Act: 0.3935. Min Act: 0.0007
Data Index: 1621937 (The Pile)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6397. Min Range: -0.6397
Max Act: 0.4135. Min Act: 0.0002
Data Index: 301318 (The Pile)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6397. Min Range: -0.6397
Max Act: 0.4130. Min Act: 0.0003
Data Index: 1294015 (The Pile)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6397. Min Range: -0.6397
Max Act: 0.3605. Min Act: 0.0013
Data Index: 1508252 (The Pile)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6397. Min Range: -0.6397
Max Act: 0.3699. Min Act: 0.0015
Data Index: 821675 (The Pile)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6397. Min Range: -0.6397
Max Act: 0.3469. Min Act: 0.0005
Data Index: 328787 (The Pile)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6397. Min Range: -0.6397
Max Act: 0.3921. Min Act: 0.0007
Data Index: 991990 (The Pile)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6397. Min Range: -0.6397
Max Act: 0.3531. Min Act: 0.0011
Data Index: 1973769 (The Pile)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6397. Min Range: -0.6397
Max Act: 0.3788. Min Act: 0.0001
Data Index: 681421 (The Pile)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6397. Min Range: -0.6397
Max Act: 0.3856. Min Act: -0.0000
Data Index: 1380891 (The Pile)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #19