Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2390. Min Range: -3.2390
Max Act: 3.2390. Min Act: -0.1700
Data Index: 6772527 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2390. Min Range: -3.2390
Max Act: 3.1604. Min Act: -0.1700
Data Index: 2894710 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2390. Min Range: -3.2390
Max Act: 3.0974. Min Act: -0.1700
Data Index: 5306715 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2390. Min Range: -3.2390
Max Act: 3.0501. Min Act: -0.1700
Data Index: 5904395 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2390. Min Range: -3.2390
Max Act: 3.0659. Min Act: -0.1700
Data Index: 3213079 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2390. Min Range: -3.2390
Max Act: 3.0816. Min Act: -0.1700
Data Index: 461872 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2390. Min Range: -3.2390
Max Act: 3.0659. Min Act: -0.1700
Data Index: 6436916 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2390. Min Range: -3.2390
Max Act: 3.0501. Min Act: -0.1700
Data Index: 5367639 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2390. Min Range: -3.2390
Max Act: 3.0501. Min Act: -0.1700
Data Index: 4649353 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2390. Min Range: -3.2390
Max Act: 3.0501. Min Act: -0.1700
Data Index: 5904396 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2390. Min Range: -3.2390
Max Act: 3.0501. Min Act: -0.1700
Data Index: 1323111 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2390. Min Range: -3.2390
Max Act: 3.0027. Min Act: -0.1700
Data Index: 7166086 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2390. Min Range: -3.2390
Max Act: 3.0185. Min Act: -0.1700
Data Index: 3823582 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2390. Min Range: -3.2390
Max Act: 3.0027. Min Act: -0.1700
Data Index: 409141 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2390. Min Range: -3.2390
Max Act: 3.0185. Min Act: -0.1700
Data Index: 6772530 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2390. Min Range: -3.2390
Max Act: 3.0185. Min Act: -0.1700
Data Index: 8672897 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2390. Min Range: -3.2390
Max Act: 3.0185. Min Act: -0.1700
Data Index: 7108274 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2390. Min Range: -3.2390
Max Act: 3.0027. Min Act: -0.1700
Data Index: 4518029 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2390. Min Range: -3.2390
Max Act: 3.0027. Min Act: -0.1700
Data Index: 5904397 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2390. Min Range: -3.2390
Max Act: 2.9711. Min Act: -0.1700
Data Index: 2315405 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19