Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2373 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0876. Min Range: -4.0876
Max Act: 4.0876. Min Act: -0.1700
Data Index: 6796861 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0876. Min Range: -4.0876
Max Act: 4.0876. Min Act: -0.1700
Data Index: 448021 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0876. Min Range: -4.0876
Max Act: 4.0250. Min Act: -0.1700
Data Index: 699854 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0876. Min Range: -4.0876
Max Act: 3.9938. Min Act: -0.1700
Data Index: 5899262 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0876. Min Range: -4.0876
Max Act: 3.9313. Min Act: -0.1700
Data Index: 7031240 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0876. Min Range: -4.0876
Max Act: 3.9000. Min Act: -0.1700
Data Index: 3278837 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0876. Min Range: -4.0876
Max Act: 3.9000. Min Act: -0.1700
Data Index: 1425475 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0876. Min Range: -4.0876
Max Act: 3.9000. Min Act: -0.1700
Data Index: 8173681 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0876. Min Range: -4.0876
Max Act: 3.8687. Min Act: -0.1700
Data Index: 215903 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0876. Min Range: -4.0876
Max Act: 3.8375. Min Act: -0.1700
Data Index: 8462643 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0876. Min Range: -4.0876
Max Act: 3.8375. Min Act: -0.1700
Data Index: 7766113 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0876. Min Range: -4.0876
Max Act: 3.8062. Min Act: -0.1700
Data Index: 7620288 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0876. Min Range: -4.0876
Max Act: 3.8062. Min Act: -0.1700
Data Index: 4930227 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0876. Min Range: -4.0876
Max Act: 3.8375. Min Act: -0.1700
Data Index: 7521239 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0876. Min Range: -4.0876
Max Act: 3.8375. Min Act: -0.1700
Data Index: 5987387 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0876. Min Range: -4.0876
Max Act: 3.8375. Min Act: -0.1700
Data Index: 4900510 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0876. Min Range: -4.0876
Max Act: 3.8375. Min Act: -0.1700
Data Index: 1485090 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0876. Min Range: -4.0876
Max Act: 3.8062. Min Act: -0.1700
Data Index: 2394105 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0876. Min Range: -4.0876
Max Act: 3.8062. Min Act: -0.1700
Data Index: 4826393 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0876. Min Range: -4.0876
Max Act: 3.8062. Min Act: -0.1700
Data Index: 4757754 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #19