Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3393 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8270. Min Range: -3.8270
Max Act: 3.8270. Min Act: -0.1700
Data Index: 7742400 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8270. Min Range: -3.8270
Max Act: 3.7644. Min Act: -0.1700
Data Index: 5965235 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8270. Min Range: -3.8270
Max Act: 3.7644. Min Act: -0.1700
Data Index: 622261 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8270. Min Range: -3.8270
Max Act: 3.7644. Min Act: -0.1700
Data Index: 4477704 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8270. Min Range: -3.8270
Max Act: 3.7332. Min Act: -0.1700
Data Index: 874509 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8270. Min Range: -3.8270
Max Act: 3.7332. Min Act: -0.1700
Data Index: 7971801 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8270. Min Range: -3.8270
Max Act: 3.7332. Min Act: -0.1700
Data Index: 1655761 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8270. Min Range: -3.8270
Max Act: 3.7332. Min Act: -0.1700
Data Index: 4036336 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8270. Min Range: -3.8270
Max Act: 3.7332. Min Act: -0.1700
Data Index: 728412 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8270. Min Range: -3.8270
Max Act: 3.7332. Min Act: -0.1700
Data Index: 295223 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8270. Min Range: -3.8270
Max Act: 3.7019. Min Act: -0.1700
Data Index: 836820 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8270. Min Range: -3.8270
Max Act: 3.6706. Min Act: -0.1700
Data Index: 3628011 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8270. Min Range: -3.8270
Max Act: 3.7019. Min Act: -0.1700
Data Index: 1188212 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8270. Min Range: -3.8270
Max Act: 3.7019. Min Act: -0.1700
Data Index: 3057694 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8270. Min Range: -3.8270
Max Act: 3.7019. Min Act: -0.1700
Data Index: 2619112 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8270. Min Range: -3.8270
Max Act: 3.7019. Min Act: -0.1700
Data Index: 2566635 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8270. Min Range: -3.8270
Max Act: 3.7019. Min Act: -0.1700
Data Index: 974391 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8270. Min Range: -3.8270
Max Act: 3.7019. Min Act: -0.1700
Data Index: 2526724 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8270. Min Range: -3.8270
Max Act: 3.7019. Min Act: -0.1700
Data Index: 927651 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8270. Min Range: -3.8270
Max Act: 3.7019. Min Act: -0.1700
Data Index: 2124271 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19