Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3541 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.7285. Min Range: -12.7285
Max Act: 12.7285. Min Act: -0.1700
Data Index: 4603214 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.7285. Min Range: -12.7285
Max Act: 12.4785. Min Act: -0.1700
Data Index: 1976790 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.7285. Min Range: -12.7285
Max Act: 12.4160. Min Act: -0.1700
Data Index: 4836191 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.7285. Min Range: -12.7285
Max Act: 12.2910. Min Act: -0.1700
Data Index: 6279205 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.7285. Min Range: -12.7285
Max Act: 12.2910. Min Act: -0.1700
Data Index: 4322092 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.7285. Min Range: -12.7285
Max Act: 12.2910. Min Act: -0.1700
Data Index: 8329402 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.7285. Min Range: -12.7285
Max Act: 12.2910. Min Act: -0.1700
Data Index: 2727911 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.7285. Min Range: -12.7285
Max Act: 12.2910. Min Act: -0.1700
Data Index: 1698973 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.7285. Min Range: -12.7285
Max Act: 12.2285. Min Act: -0.1700
Data Index: 5473968 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.7285. Min Range: -12.7285
Max Act: 12.2285. Min Act: -0.1700
Data Index: 2712070 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.7285. Min Range: -12.7285
Max Act: 12.1035. Min Act: -0.1700
Data Index: 3373091 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.7285. Min Range: -12.7285
Max Act: 12.1035. Min Act: -0.1700
Data Index: 1862466 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.7285. Min Range: -12.7285
Max Act: 12.1035. Min Act: -0.1700
Data Index: 1620848 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.7285. Min Range: -12.7285
Max Act: 12.1660. Min Act: -0.1700
Data Index: 8268660 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.7285. Min Range: -12.7285
Max Act: 12.1660. Min Act: -0.1700
Data Index: 3772796 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.7285. Min Range: -12.7285
Max Act: 12.1035. Min Act: -0.1700
Data Index: 2502550 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.7285. Min Range: -12.7285
Max Act: 12.0410. Min Act: -0.1700
Data Index: 7018801 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.7285. Min Range: -12.7285
Max Act: 12.0410. Min Act: -0.1700
Data Index: 4389446 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.7285. Min Range: -12.7285
Max Act: 11.9785. Min Act: -0.1700
Data Index: 4118808 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.7285. Min Range: -12.7285
Max Act: 11.9785. Min Act: -0.1700
Data Index: 8046420 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #19