Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4120 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9060. Min Range: -9.9060
Max Act: 9.9060. Min Act: -0.1700
Data Index: 4270813 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9060. Min Range: -9.9060
Max Act: 9.7810. Min Act: -0.1700
Data Index: 2842821 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9060. Min Range: -9.9060
Max Act: 9.7810. Min Act: -0.1700
Data Index: 2745961 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9060. Min Range: -9.9060
Max Act: 9.7185. Min Act: -0.1700
Data Index: 4630838 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9060. Min Range: -9.9060
Max Act: 9.5935. Min Act: -0.1700
Data Index: 1064619 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9060. Min Range: -9.9060
Max Act: 9.4685. Min Act: -0.1700
Data Index: 5823536 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9060. Min Range: -9.9060
Max Act: 9.5310. Min Act: -0.1700
Data Index: 5442758 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9060. Min Range: -9.9060
Max Act: 9.5310. Min Act: -0.1700
Data Index: 5429654 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9060. Min Range: -9.9060
Max Act: 9.4060. Min Act: -0.1700
Data Index: 5643850 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9060. Min Range: -9.9060
Max Act: 9.4060. Min Act: -0.1700
Data Index: 309089 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9060. Min Range: -9.9060
Max Act: 9.3435. Min Act: -0.1700
Data Index: 1980214 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9060. Min Range: -9.9060
Max Act: 9.3435. Min Act: -0.1700
Data Index: 2809335 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9060. Min Range: -9.9060
Max Act: 9.3435. Min Act: -0.1700
Data Index: 8194242 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9060. Min Range: -9.9060
Max Act: 9.4060. Min Act: -0.1700
Data Index: 1768348 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9060. Min Range: -9.9060
Max Act: 9.2810. Min Act: -0.1700
Data Index: 4230518 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9060. Min Range: -9.9060
Max Act: 9.3435. Min Act: -0.1700
Data Index: 8148570 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9060. Min Range: -9.9060
Max Act: 9.2810. Min Act: -0.1700
Data Index: 4881716 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9060. Min Range: -9.9060
Max Act: 9.2810. Min Act: -0.1700
Data Index: 5433600 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9060. Min Range: -9.9060
Max Act: 9.2185. Min Act: -0.1700
Data Index: 3718489 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9060. Min Range: -9.9060
Max Act: 9.2810. Min Act: -0.1700
Data Index: 8242232 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #19