Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3242 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1110. Min Range: -7.1110
Max Act: 7.1110. Min Act: -0.1700
Data Index: 3728222 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1110. Min Range: -7.1110
Max Act: 6.8610. Min Act: -0.1700
Data Index: 7400532 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1110. Min Range: -7.1110
Max Act: 6.8298. Min Act: -0.1700
Data Index: 7807399 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1110. Min Range: -7.1110
Max Act: 6.7673. Min Act: -0.1700
Data Index: 4286322 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1110. Min Range: -7.1110
Max Act: 6.7673. Min Act: -0.1700
Data Index: 7952418 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1110. Min Range: -7.1110
Max Act: 6.7673. Min Act: -0.1700
Data Index: 120030 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1110. Min Range: -7.1110
Max Act: 6.7360. Min Act: -0.1700
Data Index: 154831 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1110. Min Range: -7.1110
Max Act: 6.6735. Min Act: -0.1700
Data Index: 247820 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1110. Min Range: -7.1110
Max Act: 6.6735. Min Act: -0.1700
Data Index: 6563963 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1110. Min Range: -7.1110
Max Act: 6.6423. Min Act: -0.1700
Data Index: 8129863 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1110. Min Range: -7.1110
Max Act: 6.6110. Min Act: -0.1700
Data Index: 2000204 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1110. Min Range: -7.1110
Max Act: 6.6110. Min Act: -0.1700
Data Index: 6758683 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1110. Min Range: -7.1110
Max Act: 6.5485. Min Act: -0.1700
Data Index: 1906387 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1110. Min Range: -7.1110
Max Act: 6.5798. Min Act: -0.1700
Data Index: 3290497 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1110. Min Range: -7.1110
Max Act: 6.5485. Min Act: -0.1700
Data Index: 3743470 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1110. Min Range: -7.1110
Max Act: 6.5485. Min Act: -0.1700
Data Index: 474833 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1110. Min Range: -7.1110
Max Act: 6.4860. Min Act: -0.1700
Data Index: 8288516 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1110. Min Range: -7.1110
Max Act: 6.4548. Min Act: -0.1700
Data Index: 6563961 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1110. Min Range: -7.1110
Max Act: 6.4548. Min Act: -0.1700
Data Index: 2787237 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1110. Min Range: -7.1110
Max Act: 6.3923. Min Act: -0.1700
Data Index: 8631517 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #19