Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2145 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9612. Min Range: -5.9612
Max Act: 5.9612. Min Act: -0.1700
Data Index: 7863734 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9612. Min Range: -5.9612
Max Act: 5.8987. Min Act: -0.1700
Data Index: 4139368 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9612. Min Range: -5.9612
Max Act: 5.7424. Min Act: -0.1700
Data Index: 2217972 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9612. Min Range: -5.9612
Max Act: 5.7112. Min Act: -0.1700
Data Index: 374148 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9612. Min Range: -5.9612
Max Act: 5.7112. Min Act: -0.1700
Data Index: 1463033 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9612. Min Range: -5.9612
Max Act: 5.7112. Min Act: -0.1700
Data Index: 2481713 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9612. Min Range: -5.9612
Max Act: 5.6799. Min Act: -0.1700
Data Index: 7356077 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9612. Min Range: -5.9612
Max Act: 5.6487. Min Act: -0.1700
Data Index: 1622424 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9612. Min Range: -5.9612
Max Act: 5.5862. Min Act: -0.1700
Data Index: 8167184 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9612. Min Range: -5.9612
Max Act: 5.5549. Min Act: -0.1700
Data Index: 6751332 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9612. Min Range: -5.9612
Max Act: 5.5549. Min Act: -0.1700
Data Index: 7046852 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9612. Min Range: -5.9612
Max Act: 5.5549. Min Act: -0.1700
Data Index: 4638848 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9612. Min Range: -5.9612
Max Act: 5.5237. Min Act: -0.1700
Data Index: 3264998 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9612. Min Range: -5.9612
Max Act: 5.5237. Min Act: -0.1700
Data Index: 46917 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9612. Min Range: -5.9612
Max Act: 5.5237. Min Act: -0.1700
Data Index: 6432764 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9612. Min Range: -5.9612
Max Act: 5.5237. Min Act: -0.1700
Data Index: 7226164 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9612. Min Range: -5.9612
Max Act: 5.4924. Min Act: -0.1700
Data Index: 1138582 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9612. Min Range: -5.9612
Max Act: 5.4924. Min Act: -0.1700
Data Index: 6452345 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9612. Min Range: -5.9612
Max Act: 5.4924. Min Act: -0.1700
Data Index: 837761 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9612. Min Range: -5.9612
Max Act: 5.4924. Min Act: -0.1700
Data Index: 5002983 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #19