Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6331 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9583. Min Range: -7.9583
Max Act: 7.9583. Min Act: -0.1700
Data Index: 768515 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9583. Min Range: -7.9583
Max Act: 7.8958. Min Act: -0.1700
Data Index: 3203471 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9583. Min Range: -7.9583
Max Act: 7.8333. Min Act: -0.1700
Data Index: 7419061 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9583. Min Range: -7.9583
Max Act: 7.7708. Min Act: -0.1700
Data Index: 103431 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9583. Min Range: -7.9583
Max Act: 7.7083. Min Act: -0.1700
Data Index: 1702494 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9583. Min Range: -7.9583
Max Act: 7.6458. Min Act: -0.1700
Data Index: 701945 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9583. Min Range: -7.9583
Max Act: 7.5833. Min Act: -0.1700
Data Index: 667916 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9583. Min Range: -7.9583
Max Act: 7.5521. Min Act: -0.1700
Data Index: 5795558 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9583. Min Range: -7.9583
Max Act: 7.4896. Min Act: -0.1700
Data Index: 2547930 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9583. Min Range: -7.9583
Max Act: 7.4583. Min Act: -0.1700
Data Index: 6465495 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9583. Min Range: -7.9583
Max Act: 7.4271. Min Act: -0.1700
Data Index: 3501727 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9583. Min Range: -7.9583
Max Act: 7.4271. Min Act: -0.1700
Data Index: 2841044 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9583. Min Range: -7.9583
Max Act: 7.4271. Min Act: -0.1700
Data Index: 8775228 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9583. Min Range: -7.9583
Max Act: 7.4271. Min Act: -0.1700
Data Index: 7399072 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9583. Min Range: -7.9583
Max Act: 7.4271. Min Act: -0.1700
Data Index: 2041259 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9583. Min Range: -7.9583
Max Act: 7.3958. Min Act: -0.1700
Data Index: 7824798 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9583. Min Range: -7.9583
Max Act: 7.3646. Min Act: -0.1700
Data Index: 6344814 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9583. Min Range: -7.9583
Max Act: 7.3333. Min Act: -0.1700
Data Index: 1480503 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9583. Min Range: -7.9583
Max Act: 7.3333. Min Act: -0.1700
Data Index: 7399073 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9583. Min Range: -7.9583
Max Act: 7.3333. Min Act: -0.1700
Data Index: 1913086 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #19