Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2977 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4100. Min Range: -5.4100
Max Act: 5.4100. Min Act: -0.1700
Data Index: 244418 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4100. Min Range: -5.4100
Max Act: 5.3475. Min Act: -0.1700
Data Index: 8481487 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4100. Min Range: -5.4100
Max Act: 5.2850. Min Act: -0.1700
Data Index: 6004662 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4100. Min Range: -5.4100
Max Act: 5.1913. Min Act: -0.1700
Data Index: 1196634 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4100. Min Range: -5.4100
Max Act: 5.1600. Min Act: -0.1700
Data Index: 4216770 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4100. Min Range: -5.4100
Max Act: 5.1288. Min Act: -0.1700
Data Index: 878698 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4100. Min Range: -5.4100
Max Act: 5.0663. Min Act: -0.1700
Data Index: 4661656 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4100. Min Range: -5.4100
Max Act: 5.0350. Min Act: -0.1700
Data Index: 3421500 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4100. Min Range: -5.4100
Max Act: 5.0350. Min Act: -0.1700
Data Index: 8763008 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4100. Min Range: -5.4100
Max Act: 5.0350. Min Act: -0.1700
Data Index: 3735787 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4100. Min Range: -5.4100
Max Act: 5.0350. Min Act: -0.1700
Data Index: 6308572 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4100. Min Range: -5.4100
Max Act: 5.0038. Min Act: -0.1700
Data Index: 8750605 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4100. Min Range: -5.4100
Max Act: 4.9725. Min Act: -0.1700
Data Index: 7739088 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4100. Min Range: -5.4100
Max Act: 4.9725. Min Act: -0.1700
Data Index: 3478600 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4100. Min Range: -5.4100
Max Act: 4.9725. Min Act: -0.1700
Data Index: 2557320 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4100. Min Range: -5.4100
Max Act: 4.9725. Min Act: -0.1700
Data Index: 1407965 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4100. Min Range: -5.4100
Max Act: 4.9725. Min Act: -0.1700
Data Index: 1092121 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4100. Min Range: -5.4100
Max Act: 4.9725. Min Act: -0.1700
Data Index: 2371183 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4100. Min Range: -5.4100
Max Act: 4.9100. Min Act: -0.1700
Data Index: 786333 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4100. Min Range: -5.4100
Max Act: 4.9100. Min Act: -0.1700
Data Index: 1968900 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #19