Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2886 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4083. Min Range: -6.4083
Max Act: 6.4083. Min Act: -0.1700
Data Index: 4454485 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4083. Min Range: -6.4083
Max Act: 6.0646. Min Act: -0.1700
Data Index: 2825376 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4083. Min Range: -6.4083
Max Act: 6.0958. Min Act: -0.1700
Data Index: 3571854 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4083. Min Range: -6.4083
Max Act: 6.0333. Min Act: -0.1700
Data Index: 2953157 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4083. Min Range: -6.4083
Max Act: 6.0021. Min Act: -0.1700
Data Index: 4783477 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4083. Min Range: -6.4083
Max Act: 5.9083. Min Act: -0.1700
Data Index: 1517271 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4083. Min Range: -6.4083
Max Act: 5.9396. Min Act: -0.1700
Data Index: 8263305 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4083. Min Range: -6.4083
Max Act: 5.8771. Min Act: -0.1700
Data Index: 959031 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4083. Min Range: -6.4083
Max Act: 5.8771. Min Act: -0.1700
Data Index: 4559793 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4083. Min Range: -6.4083
Max Act: 5.8146. Min Act: -0.1700
Data Index: 1985230 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4083. Min Range: -6.4083
Max Act: 5.8146. Min Act: -0.1700
Data Index: 3345833 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4083. Min Range: -6.4083
Max Act: 5.8146. Min Act: -0.1700
Data Index: 2864963 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4083. Min Range: -6.4083
Max Act: 5.7208. Min Act: -0.1700
Data Index: 4753115 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4083. Min Range: -6.4083
Max Act: 5.7521. Min Act: -0.1700
Data Index: 8358976 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4083. Min Range: -6.4083
Max Act: 5.7521. Min Act: -0.1700
Data Index: 112677 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4083. Min Range: -6.4083
Max Act: 5.7208. Min Act: -0.1700
Data Index: 1499480 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4083. Min Range: -6.4083
Max Act: 5.7208. Min Act: -0.1700
Data Index: 6472942 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4083. Min Range: -6.4083
Max Act: 5.7208. Min Act: -0.1700
Data Index: 7139845 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4083. Min Range: -6.4083
Max Act: 5.7208. Min Act: -0.1700
Data Index: 7803289 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4083. Min Range: -6.4083
Max Act: 5.6583. Min Act: -0.1700
Data Index: 739932 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #19