Model: None
Dataset: The Pile
Neuron 2164 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 4.0909. Min Range: -4.0909
Max Act: 4.0909. Min Act: -0.1700
Data Index: 2383436 (The Pile)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0909. Min Range: -4.0909
Max Act: 4.0284. Min Act: -0.1700
Data Index: 10666064 (The Pile)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0909. Min Range: -4.0909
Max Act: 3.9972. Min Act: -0.1700
Data Index: 5645107 (The Pile)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0909. Min Range: -4.0909
Max Act: 3.9972. Min Act: -0.1700
Data Index: 386031 (The Pile)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0909. Min Range: -4.0909
Max Act: 3.9815. Min Act: -0.1700
Data Index: 1223802 (The Pile)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0909. Min Range: -4.0909
Max Act: 3.9659. Min Act: -0.1700
Data Index: 3051532 (The Pile)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0909. Min Range: -4.0909
Max Act: 3.9659. Min Act: -0.1700
Data Index: 672217 (The Pile)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0909. Min Range: -4.0909
Max Act: 3.9659. Min Act: -0.1700
Data Index: 10213295 (The Pile)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0909. Min Range: -4.0909
Max Act: 3.9503. Min Act: -0.1699
Data Index: 7449401 (The Pile)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0909. Min Range: -4.0909
Max Act: 3.9346. Min Act: -0.1700
Data Index: 4887718 (The Pile)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0909. Min Range: -4.0909
Max Act: 3.9346. Min Act: -0.1700
Data Index: 4743498 (The Pile)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0909. Min Range: -4.0909
Max Act: 3.9190. Min Act: -0.1700
Data Index: 8098607 (The Pile)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0909. Min Range: -4.0909
Max Act: 3.8877. Min Act: -0.1700
Data Index: 10245147 (The Pile)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0909. Min Range: -4.0909
Max Act: 3.8877. Min Act: -0.1700
Data Index: 5685167 (The Pile)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0909. Min Range: -4.0909
Max Act: 3.8877. Min Act: -0.1698
Data Index: 5387352 (The Pile)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0909. Min Range: -4.0909
Max Act: 3.8877. Min Act: -0.1700
Data Index: 9715821 (The Pile)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0909. Min Range: -4.0909
Max Act: 3.8721. Min Act: -0.1700
Data Index: 9732063 (The Pile)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0909. Min Range: -4.0909
Max Act: 3.8564. Min Act: -0.1700
Data Index: 8943310 (The Pile)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0909. Min Range: -4.0909
Max Act: 3.8408. Min Act: -0.1700
Data Index: 6979279 (The Pile)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0909. Min Range: -4.0909
Max Act: 3.8408. Min Act: -0.1700
Data Index: 9125551 (The Pile)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #19