Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2980 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7045. Min Range: -4.7045
Max Act: 4.7045. Min Act: -0.1700
Data Index: 1373807 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7045. Min Range: -4.7045
Max Act: 4.5795. Min Act: -0.1700
Data Index: 757257 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7045. Min Range: -4.7045
Max Act: 4.5169. Min Act: -0.1700
Data Index: 6672462 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7045. Min Range: -4.7045
Max Act: 4.5169. Min Act: -0.1700
Data Index: 8450739 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7045. Min Range: -4.7045
Max Act: 4.4857. Min Act: -0.1700
Data Index: 4232944 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7045. Min Range: -4.7045
Max Act: 4.4232. Min Act: -0.1700
Data Index: 6257327 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7045. Min Range: -4.7045
Max Act: 4.4544. Min Act: -0.1700
Data Index: 3088944 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7045. Min Range: -4.7045
Max Act: 4.4232. Min Act: -0.1700
Data Index: 4828730 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7045. Min Range: -4.7045
Max Act: 4.3919. Min Act: -0.1700
Data Index: 8547165 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7045. Min Range: -4.7045
Max Act: 4.4232. Min Act: -0.1700
Data Index: 1951434 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7045. Min Range: -4.7045
Max Act: 4.3919. Min Act: -0.1700
Data Index: 3088377 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7045. Min Range: -4.7045
Max Act: 4.3919. Min Act: -0.1700
Data Index: 4971617 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7045. Min Range: -4.7045
Max Act: 4.3607. Min Act: -0.1700
Data Index: 8353603 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7045. Min Range: -4.7045
Max Act: 4.3607. Min Act: -0.1700
Data Index: 4265132 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7045. Min Range: -4.7045
Max Act: 4.3607. Min Act: -0.1700
Data Index: 4046139 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7045. Min Range: -4.7045
Max Act: 4.3294. Min Act: -0.1700
Data Index: 7806133 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7045. Min Range: -4.7045
Max Act: 4.3294. Min Act: -0.1700
Data Index: 2903190 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7045. Min Range: -4.7045
Max Act: 4.2982. Min Act: -0.1700
Data Index: 3375800 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7045. Min Range: -4.7045
Max Act: 4.2982. Min Act: -0.1700
Data Index: 200794 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7045. Min Range: -4.7045
Max Act: 4.2982. Min Act: -0.1700
Data Index: 8700989 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #19