Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4762 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3157. Min Range: -7.3157
Max Act: 7.2844. Min Act: -0.1700
Data Index: 8567351 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3157. Min Range: -7.3157
Max Act: 7.3157. Min Act: -0.1700
Data Index: 6599023 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3157. Min Range: -7.3157
Max Act: 7.3157. Min Act: -0.1700
Data Index: 5949524 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3157. Min Range: -7.3157
Max Act: 7.3157. Min Act: -0.1700
Data Index: 6304608 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3157. Min Range: -7.3157
Max Act: 7.2219. Min Act: -0.1700
Data Index: 7129915 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3157. Min Range: -7.3157
Max Act: 7.1282. Min Act: -0.1700
Data Index: 7476970 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3157. Min Range: -7.3157
Max Act: 7.0657. Min Act: -0.1700
Data Index: 2390038 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3157. Min Range: -7.3157
Max Act: 7.0657. Min Act: -0.1700
Data Index: 5124834 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3157. Min Range: -7.3157
Max Act: 7.0032. Min Act: -0.1700
Data Index: 7193168 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3157. Min Range: -7.3157
Max Act: 6.9719. Min Act: -0.1700
Data Index: 8143736 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3157. Min Range: -7.3157
Max Act: 6.9719. Min Act: -0.1700
Data Index: 6931605 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3157. Min Range: -7.3157
Max Act: 7.0032. Min Act: -0.1700
Data Index: 5723833 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3157. Min Range: -7.3157
Max Act: 6.9094. Min Act: -0.1700
Data Index: 3443682 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3157. Min Range: -7.3157
Max Act: 6.9094. Min Act: -0.1700
Data Index: 1877798 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3157. Min Range: -7.3157
Max Act: 6.8782. Min Act: -0.1700
Data Index: 2524997 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3157. Min Range: -7.3157
Max Act: 6.8782. Min Act: -0.1700
Data Index: 3978084 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3157. Min Range: -7.3157
Max Act: 6.8469. Min Act: -0.1700
Data Index: 4851359 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3157. Min Range: -7.3157
Max Act: 6.7532. Min Act: -0.1700
Data Index: 2799801 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3157. Min Range: -7.3157
Max Act: 6.8157. Min Act: -0.1700
Data Index: 4838012 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3157. Min Range: -7.3157
Max Act: 6.7532. Min Act: -0.1700
Data Index: 2961789 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #19