Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4566 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2649. Min Range: -5.2649
Max Act: 5.2649. Min Act: -0.1700
Data Index: 8214660 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2649. Min Range: -5.2649
Max Act: 5.2024. Min Act: -0.1700
Data Index: 6680292 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2649. Min Range: -5.2649
Max Act: 5.1399. Min Act: -0.1700
Data Index: 4341257 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2649. Min Range: -5.2649
Max Act: 5.1086. Min Act: -0.1700
Data Index: 1805743 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2649. Min Range: -5.2649
Max Act: 5.1086. Min Act: -0.1700
Data Index: 6218526 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2649. Min Range: -5.2649
Max Act: 5.0774. Min Act: -0.1700
Data Index: 6535130 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2649. Min Range: -5.2649
Max Act: 5.1086. Min Act: -0.1700
Data Index: 5102654 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2649. Min Range: -5.2649
Max Act: 5.0774. Min Act: -0.1700
Data Index: 325427 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2649. Min Range: -5.2649
Max Act: 5.0774. Min Act: -0.1700
Data Index: 5400818 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2649. Min Range: -5.2649
Max Act: 5.0774. Min Act: -0.1700
Data Index: 8546671 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2649. Min Range: -5.2649
Max Act: 5.0149. Min Act: -0.1700
Data Index: 2651754 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2649. Min Range: -5.2649
Max Act: 5.0461. Min Act: -0.1700
Data Index: 1072099 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2649. Min Range: -5.2649
Max Act: 5.0461. Min Act: -0.1700
Data Index: 4018288 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2649. Min Range: -5.2649
Max Act: 5.0461. Min Act: -0.1700
Data Index: 5208542 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2649. Min Range: -5.2649
Max Act: 5.0149. Min Act: -0.1700
Data Index: 6454080 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2649. Min Range: -5.2649
Max Act: 5.0149. Min Act: -0.1700
Data Index: 3253625 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2649. Min Range: -5.2649
Max Act: 5.0149. Min Act: -0.1700
Data Index: 3267109 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2649. Min Range: -5.2649
Max Act: 5.0149. Min Act: -0.1700
Data Index: 2198035 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2649. Min Range: -5.2649
Max Act: 5.0149. Min Act: -0.1700
Data Index: 3683212 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2649. Min Range: -5.2649
Max Act: 5.0149. Min Act: -0.1700
Data Index: 8193933 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #19