Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2496 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4598. Min Range: -5.4598
Max Act: 5.4598. Min Act: -0.1700
Data Index: 8761713 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4598. Min Range: -5.4598
Max Act: 5.3348. Min Act: -0.1700
Data Index: 5570403 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4598. Min Range: -5.4598
Max Act: 5.3035. Min Act: -0.1700
Data Index: 2600791 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4598. Min Range: -5.4598
Max Act: 5.2410. Min Act: -0.1700
Data Index: 2631421 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4598. Min Range: -5.4598
Max Act: 5.2723. Min Act: -0.1700
Data Index: 8607108 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4598. Min Range: -5.4598
Max Act: 5.2098. Min Act: -0.1700
Data Index: 2909818 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4598. Min Range: -5.4598
Max Act: 5.1785. Min Act: -0.1700
Data Index: 8577124 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4598. Min Range: -5.4598
Max Act: 5.1785. Min Act: -0.1700
Data Index: 5991653 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4598. Min Range: -5.4598
Max Act: 5.1473. Min Act: -0.1700
Data Index: 7336717 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4598. Min Range: -5.4598
Max Act: 5.1785. Min Act: -0.1700
Data Index: 5402431 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4598. Min Range: -5.4598
Max Act: 5.1160. Min Act: -0.1700
Data Index: 513321 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4598. Min Range: -5.4598
Max Act: 5.0848. Min Act: -0.1700
Data Index: 2891954 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4598. Min Range: -5.4598
Max Act: 5.0848. Min Act: -0.1700
Data Index: 6352005 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4598. Min Range: -5.4598
Max Act: 5.0535. Min Act: -0.1700
Data Index: 7553006 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4598. Min Range: -5.4598
Max Act: 5.0535. Min Act: -0.1700
Data Index: 5856112 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4598. Min Range: -5.4598
Max Act: 5.0223. Min Act: -0.1700
Data Index: 5558602 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4598. Min Range: -5.4598
Max Act: 5.0223. Min Act: -0.1700
Data Index: 8498481 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4598. Min Range: -5.4598
Max Act: 5.0223. Min Act: -0.1700
Data Index: 33450 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4598. Min Range: -5.4598
Max Act: 5.0223. Min Act: -0.1700
Data Index: 3445801 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4598. Min Range: -5.4598
Max Act: 5.0223. Min Act: -0.1700
Data Index: 2042459 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #19