Model: None
Dataset: The Pile
Neuron 808 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-160m')
Text #0
Max Range: 3.8993. Min Range: -3.8993
Max Act: 3.8993. Min Act: -0.1700
Data Index: 1143378 (The Pile)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8993. Min Range: -3.8993
Max Act: 3.8680. Min Act: -0.1700
Data Index: 877401 (The Pile)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8993. Min Range: -3.8993
Max Act: 3.8054. Min Act: -0.1700
Data Index: 2825717 (The Pile)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8993. Min Range: -3.8993
Max Act: 3.8054. Min Act: -0.1700
Data Index: 9076005 (The Pile)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8993. Min Range: -3.8993
Max Act: 3.7429. Min Act: -0.1700
Data Index: 8432988 (The Pile)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8993. Min Range: -3.8993
Max Act: 3.7429. Min Act: -0.1700
Data Index: 1747875 (The Pile)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8993. Min Range: -3.8993
Max Act: 3.7429. Min Act: -0.1700
Data Index: 8916138 (The Pile)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8993. Min Range: -3.8993
Max Act: 3.7429. Min Act: -0.1700
Data Index: 3767579 (The Pile)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8993. Min Range: -3.8993
Max Act: 3.7116. Min Act: -0.1700
Data Index: 6922415 (The Pile)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8993. Min Range: -3.8993
Max Act: 3.7116. Min Act: -0.1700
Data Index: 9287383 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8993. Min Range: -3.8993
Max Act: 3.7116. Min Act: -0.1700
Data Index: 2882739 (The Pile)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8993. Min Range: -3.8993
Max Act: 3.7116. Min Act: -0.1700
Data Index: 7042750 (The Pile)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8993. Min Range: -3.8993
Max Act: 3.7116. Min Act: -0.1700
Data Index: 8994935 (The Pile)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8993. Min Range: -3.8993
Max Act: 3.7116. Min Act: -0.1700
Data Index: 1075955 (The Pile)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8993. Min Range: -3.8993
Max Act: 3.7116. Min Act: -0.1700
Data Index: 8826388 (The Pile)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8993. Min Range: -3.8993
Max Act: 3.7116. Min Act: -0.1700
Data Index: 613721 (The Pile)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8993. Min Range: -3.8993
Max Act: 3.6803. Min Act: -0.1700
Data Index: 3769825 (The Pile)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8993. Min Range: -3.8993
Max Act: 3.6803. Min Act: -0.1700
Data Index: 3277702 (The Pile)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8993. Min Range: -3.8993
Max Act: 3.6803. Min Act: -0.1700
Data Index: 9607143 (The Pile)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8993. Min Range: -3.8993
Max Act: 3.6803. Min Act: -0.1700
Data Index: 4967434 (The Pile)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #19