Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2874 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.4033. Min Range: -1.4033
Max Act: 1.4033. Min Act: -0.1700
Data Index: 6214213 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4033. Min Range: -1.4033
Max Act: 1.2975. Min Act: -0.1700
Data Index: 5139990 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4033. Min Range: -1.4033
Max Act: 1.2798. Min Act: -0.1700
Data Index: 4339809 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4033. Min Range: -1.4033
Max Act: 1.2798. Min Act: -0.1700
Data Index: 7390818 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4033. Min Range: -1.4033
Max Act: 1.2269. Min Act: -0.1700
Data Index: 2592097 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4033. Min Range: -1.4033
Max Act: 1.2269. Min Act: -0.1700
Data Index: 2010775 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4033. Min Range: -1.4033
Max Act: 1.2269. Min Act: -0.1700
Data Index: 7982110 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4033. Min Range: -1.4033
Max Act: 1.2093. Min Act: -0.1700
Data Index: 5775002 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4033. Min Range: -1.4033
Max Act: 1.2093. Min Act: -0.1700
Data Index: 7122649 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4033. Min Range: -1.4033
Max Act: 1.1917. Min Act: -0.1700
Data Index: 5013162 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4033. Min Range: -1.4033
Max Act: 1.1917. Min Act: -0.1700
Data Index: 5474816 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4033. Min Range: -1.4033
Max Act: 1.1917. Min Act: -0.1700
Data Index: 3134738 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4033. Min Range: -1.4033
Max Act: 1.1741. Min Act: -0.1700
Data Index: 8520633 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4033. Min Range: -1.4033
Max Act: 1.1741. Min Act: -0.1700
Data Index: 3804229 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4033. Min Range: -1.4033
Max Act: 1.1389. Min Act: -0.1700
Data Index: 1294966 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4033. Min Range: -1.4033
Max Act: 1.1565. Min Act: -0.1700
Data Index: 3704398 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4033. Min Range: -1.4033
Max Act: 1.1565. Min Act: -0.1700
Data Index: 2982426 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4033. Min Range: -1.4033
Max Act: 1.1565. Min Act: -0.1700
Data Index: 563516 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4033. Min Range: -1.4033
Max Act: 1.1565. Min Act: -0.1700
Data Index: 5704095 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4033. Min Range: -1.4033
Max Act: 1.1741. Min Act: -0.1700
Data Index: 5709532 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #19