Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4642 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0233. Min Range: -4.0233
Max Act: 4.0233. Min Act: -0.1700
Data Index: 7738112 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0233. Min Range: -4.0233
Max Act: 3.9608. Min Act: -0.1700
Data Index: 2683786 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0233. Min Range: -4.0233
Max Act: 3.8670. Min Act: -0.1700
Data Index: 5406891 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0233. Min Range: -4.0233
Max Act: 3.8670. Min Act: -0.1700
Data Index: 1216114 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0233. Min Range: -4.0233
Max Act: 3.8357. Min Act: -0.1700
Data Index: 6440902 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0233. Min Range: -4.0233
Max Act: 3.8357. Min Act: -0.1700
Data Index: 4463082 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0233. Min Range: -4.0233
Max Act: 3.8357. Min Act: -0.1700
Data Index: 5170152 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0233. Min Range: -4.0233
Max Act: 3.8357. Min Act: -0.1700
Data Index: 7162133 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0233. Min Range: -4.0233
Max Act: 3.8044. Min Act: -0.1700
Data Index: 8645544 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0233. Min Range: -4.0233
Max Act: 3.8044. Min Act: -0.1700
Data Index: 5714351 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0233. Min Range: -4.0233
Max Act: 3.8044. Min Act: -0.1700
Data Index: 6505725 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0233. Min Range: -4.0233
Max Act: 3.8357. Min Act: -0.1700
Data Index: 2080294 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0233. Min Range: -4.0233
Max Act: 3.7888. Min Act: -0.1700
Data Index: 1461971 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0233. Min Range: -4.0233
Max Act: 3.7888. Min Act: -0.1700
Data Index: 155242 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0233. Min Range: -4.0233
Max Act: 3.7888. Min Act: -0.1700
Data Index: 3704690 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0233. Min Range: -4.0233
Max Act: 3.7888. Min Act: -0.1700
Data Index: 4966941 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0233. Min Range: -4.0233
Max Act: 3.7888. Min Act: -0.1700
Data Index: 2963208 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0233. Min Range: -4.0233
Max Act: 3.7888. Min Act: -0.1700
Data Index: 1590807 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0233. Min Range: -4.0233
Max Act: 3.7888. Min Act: -0.1700
Data Index: 2666281 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0233. Min Range: -4.0233
Max Act: 3.7732. Min Act: -0.1700
Data Index: 7402528 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #19