Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1635 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1140. Min Range: -7.1140
Max Act: 7.1140. Min Act: -0.1700
Data Index: 1994767 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1140. Min Range: -7.1140
Max Act: 6.8640. Min Act: -0.1700
Data Index: 1413694 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1140. Min Range: -7.1140
Max Act: 6.8015. Min Act: -0.1700
Data Index: 5191415 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1140. Min Range: -7.1140
Max Act: 6.8327. Min Act: -0.1700
Data Index: 5340332 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1140. Min Range: -7.1140
Max Act: 6.7702. Min Act: -0.1700
Data Index: 2325069 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1140. Min Range: -7.1140
Max Act: 6.7702. Min Act: -0.1700
Data Index: 6456609 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1140. Min Range: -7.1140
Max Act: 6.7702. Min Act: -0.1700
Data Index: 1884807 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1140. Min Range: -7.1140
Max Act: 6.7390. Min Act: -0.1700
Data Index: 4551335 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1140. Min Range: -7.1140
Max Act: 6.7390. Min Act: -0.1700
Data Index: 5003738 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1140. Min Range: -7.1140
Max Act: 6.7077. Min Act: -0.1700
Data Index: 1105161 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1140. Min Range: -7.1140
Max Act: 6.6452. Min Act: -0.1700
Data Index: 5864280 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1140. Min Range: -7.1140
Max Act: 6.6140. Min Act: -0.1700
Data Index: 1299505 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1140. Min Range: -7.1140
Max Act: 6.6140. Min Act: -0.1700
Data Index: 3671097 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1140. Min Range: -7.1140
Max Act: 6.5827. Min Act: -0.1700
Data Index: 2787910 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1140. Min Range: -7.1140
Max Act: 6.5827. Min Act: -0.1700
Data Index: 8053476 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1140. Min Range: -7.1140
Max Act: 6.5515. Min Act: -0.1700
Data Index: 6496645 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1140. Min Range: -7.1140
Max Act: 6.5515. Min Act: -0.1700
Data Index: 7601593 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1140. Min Range: -7.1140
Max Act: 6.5515. Min Act: -0.1700
Data Index: 4181299 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1140. Min Range: -7.1140
Max Act: 6.4890. Min Act: -0.1700
Data Index: 260883 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1140. Min Range: -7.1140
Max Act: 6.4890. Min Act: -0.1700
Data Index: 7112962 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #19