Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1749 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1702. Min Range: -4.1702
Max Act: 4.1702. Min Act: -0.1700
Data Index: 131276 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1702. Min Range: -4.1702
Max Act: 4.1390. Min Act: -0.1700
Data Index: 3563521 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1702. Min Range: -4.1702
Max Act: 4.1077. Min Act: -0.1700
Data Index: 817993 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1702. Min Range: -4.1702
Max Act: 4.0452. Min Act: -0.1700
Data Index: 6508228 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1702. Min Range: -4.1702
Max Act: 4.0452. Min Act: -0.1700
Data Index: 3176664 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1702. Min Range: -4.1702
Max Act: 4.0140. Min Act: -0.1700
Data Index: 7037005 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1702. Min Range: -4.1702
Max Act: 4.0140. Min Act: -0.1700
Data Index: 2854436 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1702. Min Range: -4.1702
Max Act: 4.0140. Min Act: -0.1700
Data Index: 4041471 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1702. Min Range: -4.1702
Max Act: 4.0140. Min Act: -0.1700
Data Index: 1836715 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1702. Min Range: -4.1702
Max Act: 3.9202. Min Act: -0.1700
Data Index: 6498370 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1702. Min Range: -4.1702
Max Act: 3.9202. Min Act: -0.1700
Data Index: 4004556 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1702. Min Range: -4.1702
Max Act: 3.8889. Min Act: -0.1700
Data Index: 332095 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1702. Min Range: -4.1702
Max Act: 3.8576. Min Act: -0.1700
Data Index: 5070706 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1702. Min Range: -4.1702
Max Act: 3.8889. Min Act: -0.1700
Data Index: 5682032 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1702. Min Range: -4.1702
Max Act: 3.8889. Min Act: -0.1700
Data Index: 339423 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1702. Min Range: -4.1702
Max Act: 3.8889. Min Act: -0.1700
Data Index: 3823648 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1702. Min Range: -4.1702
Max Act: 3.8889. Min Act: -0.1700
Data Index: 2984220 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1702. Min Range: -4.1702
Max Act: 3.8889. Min Act: -0.1700
Data Index: 2288877 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1702. Min Range: -4.1702
Max Act: 3.9202. Min Act: -0.1700
Data Index: 2683921 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1702. Min Range: -4.1702
Max Act: 3.8576. Min Act: -0.1700
Data Index: 4835815 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #19