Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3311 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9999. Min Range: -6.9999
Max Act: 6.9999. Min Act: -0.1700
Data Index: 5032784 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9999. Min Range: -6.9999
Max Act: 6.9374. Min Act: -0.1700
Data Index: 810098 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9999. Min Range: -6.9999
Max Act: 6.7811. Min Act: -0.1700
Data Index: 7837391 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9999. Min Range: -6.9999
Max Act: 6.7811. Min Act: -0.1700
Data Index: 4782093 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9999. Min Range: -6.9999
Max Act: 6.6561. Min Act: -0.1700
Data Index: 4114733 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9999. Min Range: -6.9999
Max Act: 6.6561. Min Act: -0.1700
Data Index: 7876013 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9999. Min Range: -6.9999
Max Act: 6.5936. Min Act: -0.1700
Data Index: 3260372 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9999. Min Range: -6.9999
Max Act: 6.5936. Min Act: -0.1700
Data Index: 1575477 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9999. Min Range: -6.9999
Max Act: 6.5311. Min Act: -0.1700
Data Index: 2568617 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9999. Min Range: -6.9999
Max Act: 6.5311. Min Act: -0.1700
Data Index: 7924548 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9999. Min Range: -6.9999
Max Act: 6.4999. Min Act: -0.1700
Data Index: 6487168 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9999. Min Range: -6.9999
Max Act: 6.5311. Min Act: -0.1700
Data Index: 2453933 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9999. Min Range: -6.9999
Max Act: 6.4999. Min Act: -0.1700
Data Index: 740562 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9999. Min Range: -6.9999
Max Act: 6.4374. Min Act: -0.1700
Data Index: 6026450 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9999. Min Range: -6.9999
Max Act: 6.4061. Min Act: -0.1700
Data Index: 2533134 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9999. Min Range: -6.9999
Max Act: 6.4061. Min Act: -0.1700
Data Index: 679775 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9999. Min Range: -6.9999
Max Act: 6.4061. Min Act: -0.1700
Data Index: 845432 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9999. Min Range: -6.9999
Max Act: 6.4061. Min Act: -0.1700
Data Index: 5808797 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9999. Min Range: -6.9999
Max Act: 6.3749. Min Act: -0.1700
Data Index: 6121716 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9999. Min Range: -6.9999
Max Act: 6.3749. Min Act: -0.1700
Data Index: 7457281 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #19