Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 32 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0852. Min Range: -5.0852
Max Act: 5.0852. Min Act: -0.1700
Data Index: 5585539 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0852. Min Range: -5.0852
Max Act: 4.7102. Min Act: -0.1700
Data Index: 6157237 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0852. Min Range: -5.0852
Max Act: 4.6789. Min Act: -0.1700
Data Index: 6205941 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0852. Min Range: -5.0852
Max Act: 4.6477. Min Act: -0.1700
Data Index: 6092802 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0852. Min Range: -5.0852
Max Act: 4.6477. Min Act: -0.1700
Data Index: 1256739 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0852. Min Range: -5.0852
Max Act: 4.5852. Min Act: -0.1700
Data Index: 61484 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0852. Min Range: -5.0852
Max Act: 4.5852. Min Act: -0.1700
Data Index: 1546900 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0852. Min Range: -5.0852
Max Act: 4.5852. Min Act: -0.1700
Data Index: 2709832 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0852. Min Range: -5.0852
Max Act: 4.5852. Min Act: -0.1700
Data Index: 8135583 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0852. Min Range: -5.0852
Max Act: 4.5539. Min Act: -0.1700
Data Index: 6570849 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0852. Min Range: -5.0852
Max Act: 4.5539. Min Act: -0.1700
Data Index: 8047127 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0852. Min Range: -5.0852
Max Act: 4.5539. Min Act: -0.1700
Data Index: 1735735 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0852. Min Range: -5.0852
Max Act: 4.5227. Min Act: -0.1700
Data Index: 40571 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0852. Min Range: -5.0852
Max Act: 4.5227. Min Act: -0.1700
Data Index: 5145467 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0852. Min Range: -5.0852
Max Act: 4.4602. Min Act: -0.1700
Data Index: 1277189 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0852. Min Range: -5.0852
Max Act: 4.4602. Min Act: -0.1700
Data Index: 443326 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0852. Min Range: -5.0852
Max Act: 4.4602. Min Act: -0.1700
Data Index: 5411330 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0852. Min Range: -5.0852
Max Act: 4.4602. Min Act: -0.1700
Data Index: 7727288 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0852. Min Range: -5.0852
Max Act: 4.4602. Min Act: -0.1700
Data Index: 7575078 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0852. Min Range: -5.0852
Max Act: 4.4602. Min Act: -0.1700
Data Index: 4601814 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #19