Model: None
Dataset: The Pile
Neuron 2885 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 4.8747. Min Range: -4.8747
Max Act: 4.8747. Min Act: -0.1700
Data Index: 4580788 (The Pile)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8747. Min Range: -4.8747
Max Act: 4.7497. Min Act: -0.1700
Data Index: 10047773 (The Pile)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8747. Min Range: -4.8747
Max Act: 4.7184. Min Act: -0.1699
Data Index: 1809121 (The Pile)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8747. Min Range: -4.8747
Max Act: 4.7184. Min Act: -0.1700
Data Index: 945914 (The Pile)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8747. Min Range: -4.8747
Max Act: 4.7184. Min Act: -0.1700
Data Index: 10338303 (The Pile)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8747. Min Range: -4.8747
Max Act: 4.6559. Min Act: -0.1700
Data Index: 2228344 (The Pile)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8747. Min Range: -4.8747
Max Act: 4.6247. Min Act: -0.1700
Data Index: 1262864 (The Pile)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8747. Min Range: -4.8747
Max Act: 4.6247. Min Act: -0.1700
Data Index: 4632402 (The Pile)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8747. Min Range: -4.8747
Max Act: 4.6247. Min Act: -0.1700
Data Index: 10757875 (The Pile)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8747. Min Range: -4.8747
Max Act: 4.6247. Min Act: -0.1700
Data Index: 8604104 (The Pile)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8747. Min Range: -4.8747
Max Act: 4.5934. Min Act: -0.1700
Data Index: 9608562 (The Pile)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8747. Min Range: -4.8747
Max Act: 4.5934. Min Act: -0.1700
Data Index: 3190002 (The Pile)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8747. Min Range: -4.8747
Max Act: 4.5622. Min Act: -0.1698
Data Index: 6861182 (The Pile)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8747. Min Range: -4.8747
Max Act: 4.5622. Min Act: -0.1700
Data Index: 2705799 (The Pile)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8747. Min Range: -4.8747
Max Act: 4.5622. Min Act: -0.1700
Data Index: 4226982 (The Pile)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8747. Min Range: -4.8747
Max Act: 4.5622. Min Act: -0.1700
Data Index: 1950582 (The Pile)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8747. Min Range: -4.8747
Max Act: 4.5622. Min Act: -0.1700
Data Index: 9843694 (The Pile)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8747. Min Range: -4.8747
Max Act: 4.5309. Min Act: -0.1700
Data Index: 3482808 (The Pile)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8747. Min Range: -4.8747
Max Act: 4.4997. Min Act: -0.1700
Data Index: 4321045 (The Pile)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8747. Min Range: -4.8747
Max Act: 4.4997. Min Act: -0.1700
Data Index: 8804058 (The Pile)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #19