Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4272 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2261. Min Range: -7.2261
Max Act: 7.2261. Min Act: -0.1700
Data Index: 8653102 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2261. Min Range: -7.2261
Max Act: 7.1949. Min Act: -0.1700
Data Index: 2518674 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2261. Min Range: -7.2261
Max Act: 7.1636. Min Act: -0.1700
Data Index: 4302032 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2261. Min Range: -7.2261
Max Act: 7.0699. Min Act: -0.1700
Data Index: 6234262 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2261. Min Range: -7.2261
Max Act: 7.0074. Min Act: -0.1700
Data Index: 8171161 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2261. Min Range: -7.2261
Max Act: 7.0074. Min Act: -0.1700
Data Index: 2635037 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2261. Min Range: -7.2261
Max Act: 6.9761. Min Act: -0.1700
Data Index: 6823962 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2261. Min Range: -7.2261
Max Act: 6.9761. Min Act: -0.1700
Data Index: 7568942 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2261. Min Range: -7.2261
Max Act: 6.9761. Min Act: -0.1700
Data Index: 1969177 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2261. Min Range: -7.2261
Max Act: 6.9449. Min Act: -0.1700
Data Index: 1082594 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2261. Min Range: -7.2261
Max Act: 6.9449. Min Act: -0.1700
Data Index: 5599166 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2261. Min Range: -7.2261
Max Act: 6.9136. Min Act: -0.1700
Data Index: 969878 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2261. Min Range: -7.2261
Max Act: 6.9136. Min Act: -0.1700
Data Index: 4088669 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2261. Min Range: -7.2261
Max Act: 6.9136. Min Act: -0.1700
Data Index: 3535088 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2261. Min Range: -7.2261
Max Act: 6.9136. Min Act: -0.1700
Data Index: 2333298 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2261. Min Range: -7.2261
Max Act: 6.8824. Min Act: -0.1700
Data Index: 3326912 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2261. Min Range: -7.2261
Max Act: 6.8824. Min Act: -0.1700
Data Index: 5937065 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2261. Min Range: -7.2261
Max Act: 6.8511. Min Act: -0.1700
Data Index: 998602 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2261. Min Range: -7.2261
Max Act: 6.8824. Min Act: -0.1700
Data Index: 3742394 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2261. Min Range: -7.2261
Max Act: 6.8511. Min Act: -0.1700
Data Index: 6463384 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #19