Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5064 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6884. Min Range: -6.6884
Max Act: 6.6884. Min Act: -0.1700
Data Index: 931536 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6884. Min Range: -6.6884
Max Act: 6.5946. Min Act: -0.1700
Data Index: 3629041 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6884. Min Range: -6.6884
Max Act: 6.5946. Min Act: -0.1700
Data Index: 8470296 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6884. Min Range: -6.6884
Max Act: 6.4384. Min Act: -0.1700
Data Index: 264659 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6884. Min Range: -6.6884
Max Act: 6.4384. Min Act: -0.1700
Data Index: 4577974 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6884. Min Range: -6.6884
Max Act: 6.4071. Min Act: -0.1700
Data Index: 3548524 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6884. Min Range: -6.6884
Max Act: 6.3759. Min Act: -0.1700
Data Index: 4944464 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6884. Min Range: -6.6884
Max Act: 6.3759. Min Act: -0.1700
Data Index: 1328700 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6884. Min Range: -6.6884
Max Act: 6.3759. Min Act: -0.1700
Data Index: 214939 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6884. Min Range: -6.6884
Max Act: 6.3446. Min Act: -0.1700
Data Index: 1048707 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6884. Min Range: -6.6884
Max Act: 6.3446. Min Act: -0.1700
Data Index: 394355 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6884. Min Range: -6.6884
Max Act: 6.3446. Min Act: -0.1700
Data Index: 5944936 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6884. Min Range: -6.6884
Max Act: 6.3134. Min Act: -0.1700
Data Index: 1364011 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6884. Min Range: -6.6884
Max Act: 6.2509. Min Act: -0.1700
Data Index: 1813800 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6884. Min Range: -6.6884
Max Act: 6.2821. Min Act: -0.1700
Data Index: 6015390 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6884. Min Range: -6.6884
Max Act: 6.2509. Min Act: -0.1700
Data Index: 6716495 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6884. Min Range: -6.6884
Max Act: 6.2509. Min Act: -0.1700
Data Index: 3837846 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6884. Min Range: -6.6884
Max Act: 6.2196. Min Act: -0.1700
Data Index: 3224605 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6884. Min Range: -6.6884
Max Act: 6.2509. Min Act: -0.1700
Data Index: 648883 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6884. Min Range: -6.6884
Max Act: 6.2196. Min Act: -0.1700
Data Index: 2301002 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #19