Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 622 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0845. Min Range: -4.0845
Max Act: 4.0845. Min Act: -0.1700
Data Index: 653092 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0845. Min Range: -4.0845
Max Act: 3.9594. Min Act: -0.1700
Data Index: 8365280 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0845. Min Range: -4.0845
Max Act: 3.8969. Min Act: -0.1700
Data Index: 5813397 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0845. Min Range: -4.0845
Max Act: 3.8969. Min Act: -0.1700
Data Index: 8028123 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0845. Min Range: -4.0845
Max Act: 3.8656. Min Act: -0.1700
Data Index: 85818 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0845. Min Range: -4.0845
Max Act: 3.8969. Min Act: -0.1700
Data Index: 2198140 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0845. Min Range: -4.0845
Max Act: 3.8344. Min Act: -0.1700
Data Index: 6159180 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0845. Min Range: -4.0845
Max Act: 3.8656. Min Act: -0.1700
Data Index: 7553928 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0845. Min Range: -4.0845
Max Act: 3.8656. Min Act: -0.1700
Data Index: 1722294 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0845. Min Range: -4.0845
Max Act: 3.8656. Min Act: -0.1700
Data Index: 5533785 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0845. Min Range: -4.0845
Max Act: 3.8656. Min Act: -0.1700
Data Index: 5976035 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0845. Min Range: -4.0845
Max Act: 3.8344. Min Act: -0.1700
Data Index: 8469942 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0845. Min Range: -4.0845
Max Act: 3.8031. Min Act: -0.1700
Data Index: 2499846 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0845. Min Range: -4.0845
Max Act: 3.8031. Min Act: -0.1700
Data Index: 1984840 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0845. Min Range: -4.0845
Max Act: 3.8344. Min Act: -0.1700
Data Index: 5112629 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0845. Min Range: -4.0845
Max Act: 3.8031. Min Act: -0.1700
Data Index: 4371333 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0845. Min Range: -4.0845
Max Act: 3.8031. Min Act: -0.1700
Data Index: 4952369 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0845. Min Range: -4.0845
Max Act: 3.8031. Min Act: -0.1700
Data Index: 385191 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0845. Min Range: -4.0845
Max Act: 3.8031. Min Act: -0.1700
Data Index: 974298 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0845. Min Range: -4.0845
Max Act: 3.7718. Min Act: -0.1700
Data Index: 7873279 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #19