Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5564 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1833. Min Range: -6.1833
Max Act: 6.1833. Min Act: -0.1700
Data Index: 8303922 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1833. Min Range: -6.1833
Max Act: 6.1833. Min Act: -0.1700
Data Index: 3156209 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1833. Min Range: -6.1833
Max Act: 6.1520. Min Act: -0.1700
Data Index: 3518234 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1833. Min Range: -6.1833
Max Act: 6.0270. Min Act: -0.1700
Data Index: 4465931 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1833. Min Range: -6.1833
Max Act: 5.9958. Min Act: -0.1700
Data Index: 1342898 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1833. Min Range: -6.1833
Max Act: 5.9333. Min Act: -0.1700
Data Index: 416883 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1833. Min Range: -6.1833
Max Act: 5.9333. Min Act: -0.1700
Data Index: 7480546 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1833. Min Range: -6.1833
Max Act: 5.9020. Min Act: -0.1700
Data Index: 2784076 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1833. Min Range: -6.1833
Max Act: 5.8395. Min Act: -0.1700
Data Index: 1711221 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1833. Min Range: -6.1833
Max Act: 5.8083. Min Act: -0.1700
Data Index: 1082960 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1833. Min Range: -6.1833
Max Act: 5.7770. Min Act: -0.1700
Data Index: 7598080 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1833. Min Range: -6.1833
Max Act: 5.7770. Min Act: -0.1700
Data Index: 4532563 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1833. Min Range: -6.1833
Max Act: 5.7770. Min Act: -0.1700
Data Index: 8167391 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1833. Min Range: -6.1833
Max Act: 5.7458. Min Act: -0.1700
Data Index: 8083387 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1833. Min Range: -6.1833
Max Act: 5.7458. Min Act: -0.1700
Data Index: 5883054 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1833. Min Range: -6.1833
Max Act: 5.7458. Min Act: -0.1700
Data Index: 5096347 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1833. Min Range: -6.1833
Max Act: 5.7770. Min Act: -0.1700
Data Index: 6201160 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1833. Min Range: -6.1833
Max Act: 5.7458. Min Act: -0.1700
Data Index: 209686 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1833. Min Range: -6.1833
Max Act: 5.6833. Min Act: -0.1700
Data Index: 3443047 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1833. Min Range: -6.1833
Max Act: 5.7145. Min Act: -0.1700
Data Index: 1727528 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #19