Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2551 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4880. Min Range: -7.4880
Max Act: 7.4880. Min Act: -0.1700
Data Index: 4934931 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4880. Min Range: -7.4880
Max Act: 7.3942. Min Act: -0.1700
Data Index: 3892183 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4880. Min Range: -7.4880
Max Act: 7.4255. Min Act: -0.1700
Data Index: 3467959 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4880. Min Range: -7.4880
Max Act: 7.3630. Min Act: -0.1700
Data Index: 371071 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4880. Min Range: -7.4880
Max Act: 7.2692. Min Act: -0.1700
Data Index: 4266094 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4880. Min Range: -7.4880
Max Act: 7.1130. Min Act: -0.1700
Data Index: 4284941 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4880. Min Range: -7.4880
Max Act: 7.1442. Min Act: -0.1700
Data Index: 355205 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4880. Min Range: -7.4880
Max Act: 7.1130. Min Act: -0.1700
Data Index: 5648133 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4880. Min Range: -7.4880
Max Act: 7.0817. Min Act: -0.1700
Data Index: 4811555 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4880. Min Range: -7.4880
Max Act: 7.1130. Min Act: -0.1700
Data Index: 2358838 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4880. Min Range: -7.4880
Max Act: 7.0817. Min Act: -0.1700
Data Index: 2882737 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4880. Min Range: -7.4880
Max Act: 7.1130. Min Act: -0.1700
Data Index: 455377 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4880. Min Range: -7.4880
Max Act: 7.0192. Min Act: -0.1700
Data Index: 5205259 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4880. Min Range: -7.4880
Max Act: 7.0192. Min Act: -0.1700
Data Index: 1173743 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4880. Min Range: -7.4880
Max Act: 6.9880. Min Act: -0.1700
Data Index: 4204715 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4880. Min Range: -7.4880
Max Act: 6.9880. Min Act: -0.1700
Data Index: 6979595 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4880. Min Range: -7.4880
Max Act: 6.9255. Min Act: -0.1700
Data Index: 6142348 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4880. Min Range: -7.4880
Max Act: 6.8942. Min Act: -0.1700
Data Index: 7053425 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4880. Min Range: -7.4880
Max Act: 6.9255. Min Act: -0.1700
Data Index: 1107207 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4880. Min Range: -7.4880
Max Act: 6.8942. Min Act: -0.1700
Data Index: 616456 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #19