Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3902 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8637. Min Range: -4.8637
Max Act: 4.8637. Min Act: -0.1700
Data Index: 5099703 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8637. Min Range: -4.8637
Max Act: 4.8324. Min Act: -0.1700
Data Index: 5741872 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8637. Min Range: -4.8637
Max Act: 4.8324. Min Act: -0.1700
Data Index: 6635958 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8637. Min Range: -4.8637
Max Act: 4.8012. Min Act: -0.1700
Data Index: 1418248 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8637. Min Range: -4.8637
Max Act: 4.8012. Min Act: -0.1700
Data Index: 8021875 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8637. Min Range: -4.8637
Max Act: 4.8012. Min Act: -0.1700
Data Index: 4156045 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8637. Min Range: -4.8637
Max Act: 4.7699. Min Act: -0.1700
Data Index: 2606704 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8637. Min Range: -4.8637
Max Act: 4.7699. Min Act: -0.1700
Data Index: 1917867 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8637. Min Range: -4.8637
Max Act: 4.7387. Min Act: -0.1700
Data Index: 6937509 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8637. Min Range: -4.8637
Max Act: 4.7387. Min Act: -0.1700
Data Index: 4611775 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8637. Min Range: -4.8637
Max Act: 4.7387. Min Act: -0.1700
Data Index: 8436339 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8637. Min Range: -4.8637
Max Act: 4.7387. Min Act: -0.1700
Data Index: 4004305 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8637. Min Range: -4.8637
Max Act: 4.7387. Min Act: -0.1700
Data Index: 3434368 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8637. Min Range: -4.8637
Max Act: 4.7074. Min Act: -0.1700
Data Index: 7871238 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8637. Min Range: -4.8637
Max Act: 4.7074. Min Act: -0.1700
Data Index: 2491086 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8637. Min Range: -4.8637
Max Act: 4.6762. Min Act: -0.1700
Data Index: 6876722 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8637. Min Range: -4.8637
Max Act: 4.7074. Min Act: -0.1700
Data Index: 2791176 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8637. Min Range: -4.8637
Max Act: 4.6762. Min Act: -0.1700
Data Index: 1654936 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8637. Min Range: -4.8637
Max Act: 4.6762. Min Act: -0.1700
Data Index: 5597827 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8637. Min Range: -4.8637
Max Act: 4.6762. Min Act: -0.1700
Data Index: 5552341 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #19