Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1475 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6532. Min Range: -7.6532
Max Act: 7.6532. Min Act: -0.1700
Data Index: 8253163 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6532. Min Range: -7.6532
Max Act: 7.3094. Min Act: -0.1700
Data Index: 4031523 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6532. Min Range: -7.6532
Max Act: 7.0282. Min Act: -0.1700
Data Index: 672927 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6532. Min Range: -7.6532
Max Act: 6.9969. Min Act: -0.1700
Data Index: 7613302 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6532. Min Range: -7.6532
Max Act: 7.0282. Min Act: -0.1700
Data Index: 1769447 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6532. Min Range: -7.6532
Max Act: 6.9969. Min Act: -0.1700
Data Index: 1914717 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6532. Min Range: -7.6532
Max Act: 6.9657. Min Act: -0.1700
Data Index: 49487 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6532. Min Range: -7.6532
Max Act: 6.9032. Min Act: -0.1700
Data Index: 114573 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6532. Min Range: -7.6532
Max Act: 6.8719. Min Act: -0.1700
Data Index: 6868674 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6532. Min Range: -7.6532
Max Act: 6.8407. Min Act: -0.1700
Data Index: 3489583 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6532. Min Range: -7.6532
Max Act: 6.8407. Min Act: -0.1700
Data Index: 3120290 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6532. Min Range: -7.6532
Max Act: 6.8094. Min Act: -0.1700
Data Index: 320405 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6532. Min Range: -7.6532
Max Act: 6.7157. Min Act: -0.1700
Data Index: 4564405 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6532. Min Range: -7.6532
Max Act: 6.6844. Min Act: -0.1700
Data Index: 378340 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6532. Min Range: -7.6532
Max Act: 6.6844. Min Act: -0.1700
Data Index: 3545977 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6532. Min Range: -7.6532
Max Act: 6.6532. Min Act: -0.1700
Data Index: 8103903 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6532. Min Range: -7.6532
Max Act: 6.5594. Min Act: -0.1700
Data Index: 1962979 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6532. Min Range: -7.6532
Max Act: 6.4969. Min Act: -0.1700
Data Index: 6109747 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6532. Min Range: -7.6532
Max Act: 6.5282. Min Act: -0.1700
Data Index: 5788137 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6532. Min Range: -7.6532
Max Act: 6.5282. Min Act: -0.1700
Data Index: 3693297 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #19