Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3462 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8197. Min Range: -3.8197
Max Act: 3.8197. Min Act: -0.1700
Data Index: 5036808 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8197. Min Range: -3.8197
Max Act: 3.7572. Min Act: -0.1700
Data Index: 4115030 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8197. Min Range: -3.8197
Max Act: 3.6633. Min Act: -0.1700
Data Index: 3469126 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8197. Min Range: -3.8197
Max Act: 3.6633. Min Act: -0.1700
Data Index: 7977106 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8197. Min Range: -3.8197
Max Act: 3.6320. Min Act: -0.1700
Data Index: 7786397 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8197. Min Range: -3.8197
Max Act: 3.6007. Min Act: -0.1700
Data Index: 8340785 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8197. Min Range: -3.8197
Max Act: 3.6007. Min Act: -0.1700
Data Index: 3010286 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8197. Min Range: -3.8197
Max Act: 3.6007. Min Act: -0.1700
Data Index: 4337824 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8197. Min Range: -3.8197
Max Act: 3.6007. Min Act: -0.1700
Data Index: 2171481 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8197. Min Range: -3.8197
Max Act: 3.6007. Min Act: -0.1700
Data Index: 5834477 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8197. Min Range: -3.8197
Max Act: 3.6007. Min Act: -0.1700
Data Index: 813073 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8197. Min Range: -3.8197
Max Act: 3.5851. Min Act: -0.1700
Data Index: 1429020 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8197. Min Range: -3.8197
Max Act: 3.5537. Min Act: -0.1700
Data Index: 6968527 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8197. Min Range: -3.8197
Max Act: 3.5381. Min Act: -0.1700
Data Index: 711183 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8197. Min Range: -3.8197
Max Act: 3.5224. Min Act: -0.1700
Data Index: 3636918 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8197. Min Range: -3.8197
Max Act: 3.5068. Min Act: -0.1700
Data Index: 8486267 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8197. Min Range: -3.8197
Max Act: 3.4754. Min Act: -0.1700
Data Index: 5147526 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8197. Min Range: -3.8197
Max Act: 3.4598. Min Act: -0.1700
Data Index: 338860 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8197. Min Range: -3.8197
Max Act: 3.4598. Min Act: -0.1700
Data Index: 3520436 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8197. Min Range: -3.8197
Max Act: 3.4598. Min Act: -0.1700
Data Index: 736773 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #19