Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3065 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5687. Min Range: -3.5687
Max Act: 3.5687. Min Act: -0.1700
Data Index: 7385225 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5687. Min Range: -3.5687
Max Act: 3.5530. Min Act: -0.1700
Data Index: 4498807 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5687. Min Range: -3.5687
Max Act: 3.5374. Min Act: -0.1700
Data Index: 757922 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5687. Min Range: -3.5687
Max Act: 3.5217. Min Act: -0.1700
Data Index: 1399097 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5687. Min Range: -3.5687
Max Act: 3.5061. Min Act: -0.1700
Data Index: 1368027 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5687. Min Range: -3.5687
Max Act: 3.5061. Min Act: -0.1700
Data Index: 7495723 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5687. Min Range: -3.5687
Max Act: 3.4904. Min Act: -0.1700
Data Index: 7720033 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5687. Min Range: -3.5687
Max Act: 3.4747. Min Act: -0.1700
Data Index: 5827831 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5687. Min Range: -3.5687
Max Act: 3.4747. Min Act: -0.1700
Data Index: 7416630 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5687. Min Range: -3.5687
Max Act: 3.4747. Min Act: -0.1700
Data Index: 7502667 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5687. Min Range: -3.5687
Max Act: 3.4591. Min Act: -0.1700
Data Index: 5938429 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5687. Min Range: -3.5687
Max Act: 3.4591. Min Act: -0.1700
Data Index: 4896188 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5687. Min Range: -3.5687
Max Act: 3.4591. Min Act: -0.1700
Data Index: 1503980 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5687. Min Range: -3.5687
Max Act: 3.4591. Min Act: -0.1700
Data Index: 3458651 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5687. Min Range: -3.5687
Max Act: 3.4747. Min Act: -0.1700
Data Index: 5763956 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5687. Min Range: -3.5687
Max Act: 3.4434. Min Act: -0.1700
Data Index: 309972 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5687. Min Range: -3.5687
Max Act: 3.4434. Min Act: -0.1700
Data Index: 2241596 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5687. Min Range: -3.5687
Max Act: 3.4277. Min Act: -0.1700
Data Index: 6593412 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5687. Min Range: -3.5687
Max Act: 3.4277. Min Act: -0.1700
Data Index: 333404 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5687. Min Range: -3.5687
Max Act: 3.4277. Min Act: -0.1700
Data Index: 5578348 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #19