Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 539 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4236. Min Range: -5.4236
Max Act: 5.4236. Min Act: -0.1700
Data Index: 4568727 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4236. Min Range: -5.4236
Max Act: 5.4236. Min Act: -0.1700
Data Index: 6081904 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4236. Min Range: -5.4236
Max Act: 5.2673. Min Act: -0.1700
Data Index: 7015345 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4236. Min Range: -5.4236
Max Act: 5.2361. Min Act: -0.1700
Data Index: 1578953 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4236. Min Range: -5.4236
Max Act: 5.2048. Min Act: -0.1700
Data Index: 1818286 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4236. Min Range: -5.4236
Max Act: 5.1736. Min Act: -0.1700
Data Index: 5582796 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4236. Min Range: -5.4236
Max Act: 5.1736. Min Act: -0.1700
Data Index: 2501414 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4236. Min Range: -5.4236
Max Act: 5.1736. Min Act: -0.1700
Data Index: 3578468 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4236. Min Range: -5.4236
Max Act: 5.1736. Min Act: -0.1700
Data Index: 7221078 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4236. Min Range: -5.4236
Max Act: 5.1736. Min Act: -0.1700
Data Index: 1698043 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4236. Min Range: -5.4236
Max Act: 5.1423. Min Act: -0.1700
Data Index: 5061782 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4236. Min Range: -5.4236
Max Act: 5.1423. Min Act: -0.1700
Data Index: 119942 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4236. Min Range: -5.4236
Max Act: 5.1423. Min Act: -0.1700
Data Index: 6511012 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4236. Min Range: -5.4236
Max Act: 5.1423. Min Act: -0.1700
Data Index: 8690208 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4236. Min Range: -5.4236
Max Act: 5.1736. Min Act: -0.1700
Data Index: 8087774 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4236. Min Range: -5.4236
Max Act: 5.0798. Min Act: -0.1700
Data Index: 1172625 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4236. Min Range: -5.4236
Max Act: 5.0486. Min Act: -0.1700
Data Index: 4146599 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4236. Min Range: -5.4236
Max Act: 5.0798. Min Act: -0.1700
Data Index: 7962954 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4236. Min Range: -5.4236
Max Act: 5.0486. Min Act: -0.1700
Data Index: 3748757 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4236. Min Range: -5.4236
Max Act: 5.0486. Min Act: -0.1700
Data Index: 2113813 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #19