Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4894 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3861. Min Range: -7.3861
Max Act: 7.3861. Min Act: -0.1700
Data Index: 4895077 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3861. Min Range: -7.3861
Max Act: 7.3548. Min Act: -0.1700
Data Index: 169207 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3861. Min Range: -7.3861
Max Act: 7.1673. Min Act: -0.1700
Data Index: 1910299 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3861. Min Range: -7.3861
Max Act: 7.1361. Min Act: -0.1700
Data Index: 1314402 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3861. Min Range: -7.3861
Max Act: 7.1048. Min Act: -0.1700
Data Index: 804945 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3861. Min Range: -7.3861
Max Act: 7.0423. Min Act: -0.1700
Data Index: 8598086 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3861. Min Range: -7.3861
Max Act: 6.8861. Min Act: -0.1700
Data Index: 5178959 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3861. Min Range: -7.3861
Max Act: 6.8548. Min Act: -0.1700
Data Index: 2427468 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3861. Min Range: -7.3861
Max Act: 6.8548. Min Act: -0.1700
Data Index: 5607668 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3861. Min Range: -7.3861
Max Act: 6.8236. Min Act: -0.1700
Data Index: 4478383 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3861. Min Range: -7.3861
Max Act: 6.8236. Min Act: -0.1700
Data Index: 8797110 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3861. Min Range: -7.3861
Max Act: 6.8236. Min Act: -0.1700
Data Index: 487037 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3861. Min Range: -7.3861
Max Act: 6.7611. Min Act: -0.1700
Data Index: 5977174 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3861. Min Range: -7.3861
Max Act: 6.7611. Min Act: -0.1700
Data Index: 6577745 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3861. Min Range: -7.3861
Max Act: 6.6986. Min Act: -0.1700
Data Index: 1932261 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3861. Min Range: -7.3861
Max Act: 6.6986. Min Act: -0.1700
Data Index: 4316334 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3861. Min Range: -7.3861
Max Act: 6.6673. Min Act: -0.1700
Data Index: 5064952 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3861. Min Range: -7.3861
Max Act: 6.6673. Min Act: -0.1700
Data Index: 7385963 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3861. Min Range: -7.3861
Max Act: 6.6361. Min Act: -0.1700
Data Index: 6945989 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3861. Min Range: -7.3861
Max Act: 6.6048. Min Act: -0.1700
Data Index: 1511909 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #19