Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3472 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9469. Min Range: -5.9469
Max Act: 5.9469. Min Act: -0.1700
Data Index: 734800 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9469. Min Range: -5.9469
Max Act: 5.8531. Min Act: -0.1700
Data Index: 734815 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9469. Min Range: -5.9469
Max Act: 5.8531. Min Act: -0.1700
Data Index: 5101343 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9469. Min Range: -5.9469
Max Act: 5.7906. Min Act: -0.1700
Data Index: 4294257 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9469. Min Range: -5.9469
Max Act: 5.7281. Min Act: -0.1700
Data Index: 734798 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9469. Min Range: -5.9469
Max Act: 5.7281. Min Act: -0.1700
Data Index: 2700320 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9469. Min Range: -5.9469
Max Act: 5.6344. Min Act: -0.1700
Data Index: 6259253 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9469. Min Range: -5.9469
Max Act: 5.6344. Min Act: -0.1700
Data Index: 4734966 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9469. Min Range: -5.9469
Max Act: 5.6031. Min Act: -0.1700
Data Index: 734804 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9469. Min Range: -5.9469
Max Act: 5.6031. Min Act: -0.1700
Data Index: 734801 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9469. Min Range: -5.9469
Max Act: 5.5094. Min Act: -0.1700
Data Index: 59046 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9469. Min Range: -5.9469
Max Act: 5.3844. Min Act: -0.1700
Data Index: 7043590 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9469. Min Range: -5.9469
Max Act: 5.3531. Min Act: -0.1700
Data Index: 8106384 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9469. Min Range: -5.9469
Max Act: 5.3531. Min Act: -0.1700
Data Index: 7983710 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9469. Min Range: -5.9469
Max Act: 5.3219. Min Act: -0.1700
Data Index: 7659112 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9469. Min Range: -5.9469
Max Act: 5.3531. Min Act: -0.1700
Data Index: 6494141 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9469. Min Range: -5.9469
Max Act: 5.3531. Min Act: -0.1700
Data Index: 477585 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9469. Min Range: -5.9469
Max Act: 5.2906. Min Act: -0.1700
Data Index: 1707693 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9469. Min Range: -5.9469
Max Act: 5.2906. Min Act: -0.1700
Data Index: 1912305 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9469. Min Range: -5.9469
Max Act: 5.2906. Min Act: -0.1700
Data Index: 1224658 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #19