Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2197 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2973. Min Range: -7.2973
Max Act: 7.2661. Min Act: -0.1700
Data Index: 1774639 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2973. Min Range: -7.2973
Max Act: 7.2973. Min Act: -0.1700
Data Index: 7654446 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2973. Min Range: -7.2973
Max Act: 7.2661. Min Act: -0.1700
Data Index: 5797430 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2973. Min Range: -7.2973
Max Act: 7.2348. Min Act: -0.1700
Data Index: 1455109 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2973. Min Range: -7.2973
Max Act: 7.2036. Min Act: -0.1700
Data Index: 4280694 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2973. Min Range: -7.2973
Max Act: 7.2036. Min Act: -0.1700
Data Index: 6117945 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2973. Min Range: -7.2973
Max Act: 7.2036. Min Act: -0.1700
Data Index: 5457685 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2973. Min Range: -7.2973
Max Act: 7.2348. Min Act: -0.1700
Data Index: 6796149 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2973. Min Range: -7.2973
Max Act: 7.2036. Min Act: -0.1700
Data Index: 241723 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2973. Min Range: -7.2973
Max Act: 7.1723. Min Act: -0.1700
Data Index: 5240791 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2973. Min Range: -7.2973
Max Act: 7.1411. Min Act: -0.1700
Data Index: 646632 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2973. Min Range: -7.2973
Max Act: 7.1411. Min Act: -0.1700
Data Index: 1234222 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2973. Min Range: -7.2973
Max Act: 7.1723. Min Act: -0.1700
Data Index: 3919022 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2973. Min Range: -7.2973
Max Act: 7.1411. Min Act: -0.1700
Data Index: 7586108 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2973. Min Range: -7.2973
Max Act: 7.1411. Min Act: -0.1700
Data Index: 7105245 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2973. Min Range: -7.2973
Max Act: 7.1098. Min Act: -0.1700
Data Index: 7471954 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2973. Min Range: -7.2973
Max Act: 7.0786. Min Act: -0.1700
Data Index: 1409979 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2973. Min Range: -7.2973
Max Act: 7.0473. Min Act: -0.1700
Data Index: 5626073 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2973. Min Range: -7.2973
Max Act: 7.0786. Min Act: -0.1700
Data Index: 2493653 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2973. Min Range: -7.2973
Max Act: 7.1098. Min Act: -0.1700
Data Index: 7804599 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #19