Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2310 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9556. Min Range: -3.9556
Max Act: 3.9556. Min Act: -0.1700
Data Index: 3945643 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9556. Min Range: -3.9556
Max Act: 3.8618. Min Act: -0.1700
Data Index: 8229829 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9556. Min Range: -3.9556
Max Act: 3.8618. Min Act: -0.1700
Data Index: 2138900 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9556. Min Range: -3.9556
Max Act: 3.8305. Min Act: -0.1700
Data Index: 1069501 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9556. Min Range: -3.9556
Max Act: 3.8305. Min Act: -0.1700
Data Index: 6549798 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9556. Min Range: -3.9556
Max Act: 3.8305. Min Act: -0.1700
Data Index: 4893495 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9556. Min Range: -3.9556
Max Act: 3.8305. Min Act: -0.1700
Data Index: 1839909 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9556. Min Range: -3.9556
Max Act: 3.7992. Min Act: -0.1700
Data Index: 2553226 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9556. Min Range: -3.9556
Max Act: 3.7992. Min Act: -0.1700
Data Index: 3579950 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9556. Min Range: -3.9556
Max Act: 3.7992. Min Act: -0.1700
Data Index: 6045320 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9556. Min Range: -3.9556
Max Act: 3.7992. Min Act: -0.1700
Data Index: 4980978 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9556. Min Range: -3.9556
Max Act: 3.7992. Min Act: -0.1700
Data Index: 2930992 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9556. Min Range: -3.9556
Max Act: 3.7680. Min Act: -0.1700
Data Index: 1947941 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9556. Min Range: -3.9556
Max Act: 3.7680. Min Act: -0.1700
Data Index: 1736625 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9556. Min Range: -3.9556
Max Act: 3.7680. Min Act: -0.1700
Data Index: 4135392 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9556. Min Range: -3.9556
Max Act: 3.7680. Min Act: -0.1700
Data Index: 3103716 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9556. Min Range: -3.9556
Max Act: 3.7680. Min Act: -0.1700
Data Index: 4077507 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9556. Min Range: -3.9556
Max Act: 3.7680. Min Act: -0.1700
Data Index: 75154 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9556. Min Range: -3.9556
Max Act: 3.7680. Min Act: -0.1700
Data Index: 2376770 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9556. Min Range: -3.9556
Max Act: 3.7680. Min Act: -0.1700
Data Index: 8138191 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19