Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3166 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.9160. Min Range: -7.9160
Max Act: 7.9160. Min Act: -0.1700
Data Index: 1904476 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9160. Min Range: -7.9160
Max Act: 7.8535. Min Act: -0.1700
Data Index: 4791709 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9160. Min Range: -7.9160
Max Act: 7.6347. Min Act: -0.1700
Data Index: 7692722 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9160. Min Range: -7.9160
Max Act: 7.6035. Min Act: -0.1700
Data Index: 1262681 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9160. Min Range: -7.9160
Max Act: 7.6035. Min Act: -0.1700
Data Index: 3070174 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9160. Min Range: -7.9160
Max Act: 7.5722. Min Act: -0.1700
Data Index: 5758832 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9160. Min Range: -7.9160
Max Act: 7.5410. Min Act: -0.1700
Data Index: 823019 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9160. Min Range: -7.9160
Max Act: 7.5722. Min Act: -0.1700
Data Index: 8068652 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9160. Min Range: -7.9160
Max Act: 7.4785. Min Act: -0.1700
Data Index: 8292709 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9160. Min Range: -7.9160
Max Act: 7.4785. Min Act: -0.1700
Data Index: 4818116 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9160. Min Range: -7.9160
Max Act: 7.4785. Min Act: -0.1700
Data Index: 6457185 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9160. Min Range: -7.9160
Max Act: 7.4472. Min Act: -0.1700
Data Index: 8047387 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9160. Min Range: -7.9160
Max Act: 7.4472. Min Act: -0.1700
Data Index: 6763719 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9160. Min Range: -7.9160
Max Act: 7.4472. Min Act: -0.1700
Data Index: 2139224 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9160. Min Range: -7.9160
Max Act: 7.4472. Min Act: -0.1700
Data Index: 4654961 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9160. Min Range: -7.9160
Max Act: 7.4472. Min Act: -0.1700
Data Index: 6904679 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9160. Min Range: -7.9160
Max Act: 7.4472. Min Act: -0.1700
Data Index: 6318281 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9160. Min Range: -7.9160
Max Act: 7.4160. Min Act: -0.1700
Data Index: 4754387 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9160. Min Range: -7.9160
Max Act: 7.4160. Min Act: -0.1700
Data Index: 7904369 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9160. Min Range: -7.9160
Max Act: 7.4160. Min Act: -0.1700
Data Index: 7157930 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #19