Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3056 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1133. Min Range: -6.1133
Max Act: 6.1133. Min Act: -0.1700
Data Index: 2628588 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1133. Min Range: -6.1133
Max Act: 6.1133. Min Act: -0.1700
Data Index: 6226586 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1133. Min Range: -6.1133
Max Act: 6.0195. Min Act: -0.1700
Data Index: 3826510 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1133. Min Range: -6.1133
Max Act: 5.9570. Min Act: -0.1700
Data Index: 4368745 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1133. Min Range: -6.1133
Max Act: 5.9258. Min Act: -0.1700
Data Index: 5608551 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1133. Min Range: -6.1133
Max Act: 5.7695. Min Act: -0.1700
Data Index: 4093204 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1133. Min Range: -6.1133
Max Act: 5.8008. Min Act: -0.1700
Data Index: 7388964 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1133. Min Range: -6.1133
Max Act: 5.8320. Min Act: -0.1700
Data Index: 2818886 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1133. Min Range: -6.1133
Max Act: 5.7383. Min Act: -0.1700
Data Index: 2895762 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1133. Min Range: -6.1133
Max Act: 5.7070. Min Act: -0.1700
Data Index: 636947 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1133. Min Range: -6.1133
Max Act: 5.7070. Min Act: -0.1700
Data Index: 4429743 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1133. Min Range: -6.1133
Max Act: 5.6758. Min Act: -0.1700
Data Index: 6206889 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1133. Min Range: -6.1133
Max Act: 5.7070. Min Act: -0.1700
Data Index: 6574012 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1133. Min Range: -6.1133
Max Act: 5.6758. Min Act: -0.1700
Data Index: 6940699 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1133. Min Range: -6.1133
Max Act: 5.6758. Min Act: -0.1700
Data Index: 6159750 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1133. Min Range: -6.1133
Max Act: 5.6133. Min Act: -0.1700
Data Index: 8601437 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1133. Min Range: -6.1133
Max Act: 5.6133. Min Act: -0.1700
Data Index: 8400128 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1133. Min Range: -6.1133
Max Act: 5.6133. Min Act: -0.1700
Data Index: 6654455 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1133. Min Range: -6.1133
Max Act: 5.5820. Min Act: -0.1700
Data Index: 7229242 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1133. Min Range: -6.1133
Max Act: 5.6133. Min Act: -0.1700
Data Index: 6401051 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #19