Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 792 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9501. Min Range: -5.9501
Max Act: 5.9501. Min Act: -0.1700
Data Index: 5351846 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9501. Min Range: -5.9501
Max Act: 5.9501. Min Act: -0.1700
Data Index: 2680997 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9501. Min Range: -5.9501
Max Act: 5.7938. Min Act: -0.1700
Data Index: 5948419 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9501. Min Range: -5.9501
Max Act: 5.7313. Min Act: -0.1700
Data Index: 6437945 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9501. Min Range: -5.9501
Max Act: 5.7313. Min Act: -0.1700
Data Index: 4063271 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9501. Min Range: -5.9501
Max Act: 5.7313. Min Act: -0.1700
Data Index: 1600344 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9501. Min Range: -5.9501
Max Act: 5.7313. Min Act: -0.1700
Data Index: 2553161 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9501. Min Range: -5.9501
Max Act: 5.6688. Min Act: -0.1700
Data Index: 822926 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9501. Min Range: -5.9501
Max Act: 5.6688. Min Act: -0.1700
Data Index: 8124046 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9501. Min Range: -5.9501
Max Act: 5.6376. Min Act: -0.1700
Data Index: 3986967 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9501. Min Range: -5.9501
Max Act: 5.6376. Min Act: -0.1700
Data Index: 7323339 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9501. Min Range: -5.9501
Max Act: 5.6376. Min Act: -0.1700
Data Index: 3741294 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9501. Min Range: -5.9501
Max Act: 5.6376. Min Act: -0.1700
Data Index: 8173634 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9501. Min Range: -5.9501
Max Act: 5.6063. Min Act: -0.1700
Data Index: 7873779 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9501. Min Range: -5.9501
Max Act: 5.6063. Min Act: -0.1700
Data Index: 403814 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9501. Min Range: -5.9501
Max Act: 5.6063. Min Act: -0.1700
Data Index: 2810655 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9501. Min Range: -5.9501
Max Act: 5.6376. Min Act: -0.1700
Data Index: 4370040 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9501. Min Range: -5.9501
Max Act: 5.6376. Min Act: -0.1700
Data Index: 8566852 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9501. Min Range: -5.9501
Max Act: 5.6063. Min Act: -0.1700
Data Index: 1036529 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9501. Min Range: -5.9501
Max Act: 5.5751. Min Act: -0.1700
Data Index: 5391500 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #19