Model: None
Dataset: The Pile
Neuron 2464 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 2.8647. Min Range: -2.8647
Max Act: 2.8647. Min Act: -0.1700
Data Index: 687800 (The Pile)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8647. Min Range: -2.8647
Max Act: 2.8330. Min Act: -0.1700
Data Index: 9415834 (The Pile)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8647. Min Range: -2.8647
Max Act: 2.8170. Min Act: -0.1700
Data Index: 4226506 (The Pile)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8647. Min Range: -2.8647
Max Act: 2.8170. Min Act: -0.1700
Data Index: 28111 (The Pile)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8647. Min Range: -2.8647
Max Act: 2.8011. Min Act: -0.1700
Data Index: 7737840 (The Pile)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8647. Min Range: -2.8647
Max Act: 2.7852. Min Act: -0.1700
Data Index: 8362332 (The Pile)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8647. Min Range: -2.8647
Max Act: 2.7533. Min Act: -0.1700
Data Index: 594716 (The Pile)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8647. Min Range: -2.8647
Max Act: 2.7533. Min Act: -0.1700
Data Index: 6100763 (The Pile)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8647. Min Range: -2.8647
Max Act: 2.7214. Min Act: -0.1700
Data Index: 9572388 (The Pile)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8647. Min Range: -2.8647
Max Act: 2.7214. Min Act: -0.1700
Data Index: 4988389 (The Pile)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8647. Min Range: -2.8647
Max Act: 2.7214. Min Act: -0.1700
Data Index: 9327024 (The Pile)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8647. Min Range: -2.8647
Max Act: 2.7054. Min Act: -0.1700
Data Index: 6019201 (The Pile)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8647. Min Range: -2.8647
Max Act: 2.7054. Min Act: -0.1700
Data Index: 9479509 (The Pile)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8647. Min Range: -2.8647
Max Act: 2.7054. Min Act: -0.1700
Data Index: 2965859 (The Pile)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8647. Min Range: -2.8647
Max Act: 2.7054. Min Act: -0.1700
Data Index: 3098527 (The Pile)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8647. Min Range: -2.8647
Max Act: 2.6894. Min Act: -0.1700
Data Index: 6035287 (The Pile)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8647. Min Range: -2.8647
Max Act: 2.6894. Min Act: -0.1700
Data Index: 4139821 (The Pile)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8647. Min Range: -2.8647
Max Act: 2.6894. Min Act: -0.1700
Data Index: 5770868 (The Pile)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8647. Min Range: -2.8647
Max Act: 2.6894. Min Act: -0.1700
Data Index: 1060958 (The Pile)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8647. Min Range: -2.8647
Max Act: 2.6894. Min Act: -0.1700
Data Index: 3449881 (The Pile)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #19