Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2127 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1362. Min Range: -4.1362
Max Act: 4.1362. Min Act: -0.1700
Data Index: 5790471 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1362. Min Range: -4.1362
Max Act: 4.0737. Min Act: -0.1700
Data Index: 2318976 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1362. Min Range: -4.1362
Max Act: 4.0737. Min Act: -0.1700
Data Index: 4822658 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1362. Min Range: -4.1362
Max Act: 4.0737. Min Act: -0.1700
Data Index: 2931013 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1362. Min Range: -4.1362
Max Act: 4.0112. Min Act: -0.1700
Data Index: 2201972 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1362. Min Range: -4.1362
Max Act: 4.0112. Min Act: -0.1700
Data Index: 4548852 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1362. Min Range: -4.1362
Max Act: 3.9799. Min Act: -0.1700
Data Index: 234518 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1362. Min Range: -4.1362
Max Act: 3.9799. Min Act: -0.1700
Data Index: 100891 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1362. Min Range: -4.1362
Max Act: 3.9799. Min Act: -0.1700
Data Index: 613004 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1362. Min Range: -4.1362
Max Act: 3.9799. Min Act: -0.1700
Data Index: 613005 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1362. Min Range: -4.1362
Max Act: 3.9799. Min Act: -0.1700
Data Index: 5279635 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1362. Min Range: -4.1362
Max Act: 3.9799. Min Act: -0.1700
Data Index: 595239 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1362. Min Range: -4.1362
Max Act: 3.9486. Min Act: -0.1700
Data Index: 5910230 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1362. Min Range: -4.1362
Max Act: 3.9486. Min Act: -0.1700
Data Index: 234519 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1362. Min Range: -4.1362
Max Act: 3.9486. Min Act: -0.1700
Data Index: 2915792 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1362. Min Range: -4.1362
Max Act: 3.9486. Min Act: -0.1700
Data Index: 7656318 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1362. Min Range: -4.1362
Max Act: 3.8861. Min Act: -0.1700
Data Index: 1671815 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1362. Min Range: -4.1362
Max Act: 3.9174. Min Act: -0.1700
Data Index: 1348865 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1362. Min Range: -4.1362
Max Act: 3.9486. Min Act: -0.1700
Data Index: 401761 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1362. Min Range: -4.1362
Max Act: 3.8861. Min Act: -0.1700
Data Index: 663937 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #19