Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2677 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9629. Min Range: -6.9629
Max Act: 6.9629. Min Act: -0.1700
Data Index: 8448149 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9629. Min Range: -6.9629
Max Act: 6.8691. Min Act: -0.1700
Data Index: 7081762 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9629. Min Range: -6.9629
Max Act: 6.7754. Min Act: -0.1700
Data Index: 6231152 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9629. Min Range: -6.9629
Max Act: 6.7441. Min Act: -0.1700
Data Index: 1542086 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9629. Min Range: -6.9629
Max Act: 6.7441. Min Act: -0.1700
Data Index: 1896830 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9629. Min Range: -6.9629
Max Act: 6.7441. Min Act: -0.1700
Data Index: 1673158 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9629. Min Range: -6.9629
Max Act: 6.7441. Min Act: -0.1700
Data Index: 5069716 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9629. Min Range: -6.9629
Max Act: 6.7441. Min Act: -0.1700
Data Index: 7759404 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9629. Min Range: -6.9629
Max Act: 6.6504. Min Act: -0.1700
Data Index: 4825273 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9629. Min Range: -6.9629
Max Act: 6.6816. Min Act: -0.1700
Data Index: 3744565 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9629. Min Range: -6.9629
Max Act: 6.6816. Min Act: -0.1700
Data Index: 8187413 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9629. Min Range: -6.9629
Max Act: 6.6191. Min Act: -0.1700
Data Index: 1534777 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9629. Min Range: -6.9629
Max Act: 6.6504. Min Act: -0.1700
Data Index: 1936239 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9629. Min Range: -6.9629
Max Act: 6.6504. Min Act: -0.1700
Data Index: 8727391 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9629. Min Range: -6.9629
Max Act: 6.6504. Min Act: -0.1700
Data Index: 775801 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9629. Min Range: -6.9629
Max Act: 6.6504. Min Act: -0.1700
Data Index: 1749715 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9629. Min Range: -6.9629
Max Act: 6.6504. Min Act: -0.1700
Data Index: 3530546 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9629. Min Range: -6.9629
Max Act: 6.6191. Min Act: -0.1700
Data Index: 8172995 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9629. Min Range: -6.9629
Max Act: 6.6191. Min Act: -0.1700
Data Index: 4000079 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9629. Min Range: -6.9629
Max Act: 6.6191. Min Act: -0.1700
Data Index: 2624520 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19