Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2460 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4755. Min Range: -3.4755
Max Act: 3.4755. Min Act: -0.1700
Data Index: 387633 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4755. Min Range: -3.4755
Max Act: 3.4755. Min Act: -0.1700
Data Index: 6158284 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4755. Min Range: -3.4755
Max Act: 3.4285. Min Act: -0.1700
Data Index: 5974916 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4755. Min Range: -3.4755
Max Act: 3.3658. Min Act: -0.1700
Data Index: 8084976 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4755. Min Range: -3.4755
Max Act: 3.3501. Min Act: -0.1700
Data Index: 5430662 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4755. Min Range: -3.4755
Max Act: 3.3658. Min Act: -0.1700
Data Index: 2638866 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4755. Min Range: -3.4755
Max Act: 3.3658. Min Act: -0.1700
Data Index: 7873632 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4755. Min Range: -3.4755
Max Act: 3.3501. Min Act: -0.1700
Data Index: 5768631 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4755. Min Range: -3.4755
Max Act: 3.3658. Min Act: -0.1700
Data Index: 6871458 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4755. Min Range: -3.4755
Max Act: 3.3344. Min Act: -0.1700
Data Index: 8154591 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4755. Min Range: -3.4755
Max Act: 3.3501. Min Act: -0.1700
Data Index: 8051320 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4755. Min Range: -3.4755
Max Act: 3.3344. Min Act: -0.1700
Data Index: 5735541 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4755. Min Range: -3.4755
Max Act: 3.3187. Min Act: -0.1700
Data Index: 5901224 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4755. Min Range: -3.4755
Max Act: 3.3187. Min Act: -0.1700
Data Index: 4406834 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4755. Min Range: -3.4755
Max Act: 3.2873. Min Act: -0.1700
Data Index: 2988332 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4755. Min Range: -3.4755
Max Act: 3.3030. Min Act: -0.1700
Data Index: 1958098 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4755. Min Range: -3.4755
Max Act: 3.2873. Min Act: -0.1700
Data Index: 4164426 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4755. Min Range: -3.4755
Max Act: 3.2559. Min Act: -0.1700
Data Index: 4197747 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4755. Min Range: -3.4755
Max Act: 3.2559. Min Act: -0.1700
Data Index: 1045168 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4755. Min Range: -3.4755
Max Act: 3.2559. Min Act: -0.1700
Data Index: 5652706 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #19