Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2648 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.0061. Min Range: -8.0061
Max Act: 8.0061. Min Act: -0.1700
Data Index: 389306 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0061. Min Range: -8.0061
Max Act: 7.9436. Min Act: -0.1700
Data Index: 4368593 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0061. Min Range: -8.0061
Max Act: 7.9124. Min Act: -0.1700
Data Index: 2763196 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0061. Min Range: -8.0061
Max Act: 7.8811. Min Act: -0.1700
Data Index: 7858785 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0061. Min Range: -8.0061
Max Act: 7.8811. Min Act: -0.1700
Data Index: 5605796 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0061. Min Range: -8.0061
Max Act: 7.8811. Min Act: -0.1700
Data Index: 8643445 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0061. Min Range: -8.0061
Max Act: 7.8499. Min Act: -0.1700
Data Index: 4595151 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0061. Min Range: -8.0061
Max Act: 7.8499. Min Act: -0.1700
Data Index: 3946144 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0061. Min Range: -8.0061
Max Act: 7.8186. Min Act: -0.1700
Data Index: 3623761 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0061. Min Range: -8.0061
Max Act: 7.8186. Min Act: -0.1700
Data Index: 4305967 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0061. Min Range: -8.0061
Max Act: 7.7874. Min Act: -0.1700
Data Index: 3630348 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0061. Min Range: -8.0061
Max Act: 7.7874. Min Act: -0.1700
Data Index: 5837984 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0061. Min Range: -8.0061
Max Act: 7.7874. Min Act: -0.1700
Data Index: 4223265 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0061. Min Range: -8.0061
Max Act: 7.7561. Min Act: -0.1700
Data Index: 530967 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0061. Min Range: -8.0061
Max Act: 7.7561. Min Act: -0.1700
Data Index: 6878976 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0061. Min Range: -8.0061
Max Act: 7.7249. Min Act: -0.1700
Data Index: 6273066 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0061. Min Range: -8.0061
Max Act: 7.7249. Min Act: -0.1700
Data Index: 7314398 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0061. Min Range: -8.0061
Max Act: 7.6936. Min Act: -0.1700
Data Index: 284952 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0061. Min Range: -8.0061
Max Act: 7.6936. Min Act: -0.1700
Data Index: 2237479 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0061. Min Range: -8.0061
Max Act: 7.7249. Min Act: -0.1700
Data Index: 5011849 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #19