Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2186 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9620. Min Range: -7.9620
Max Act: 7.9620. Min Act: -0.1700
Data Index: 5481188 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9620. Min Range: -7.9620
Max Act: 7.9620. Min Act: -0.1700
Data Index: 121777 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9620. Min Range: -7.9620
Max Act: 7.8995. Min Act: -0.1700
Data Index: 6680024 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9620. Min Range: -7.9620
Max Act: 7.8370. Min Act: -0.1700
Data Index: 6025759 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9620. Min Range: -7.9620
Max Act: 7.7745. Min Act: -0.1700
Data Index: 1727772 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9620. Min Range: -7.9620
Max Act: 7.7745. Min Act: -0.1700
Data Index: 4218376 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9620. Min Range: -7.9620
Max Act: 7.7120. Min Act: -0.1700
Data Index: 514240 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9620. Min Range: -7.9620
Max Act: 7.7120. Min Act: -0.1700
Data Index: 2883951 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9620. Min Range: -7.9620
Max Act: 7.7120. Min Act: -0.1700
Data Index: 4804151 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9620. Min Range: -7.9620
Max Act: 7.7120. Min Act: -0.1700
Data Index: 1194630 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9620. Min Range: -7.9620
Max Act: 7.7433. Min Act: -0.1700
Data Index: 2310542 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9620. Min Range: -7.9620
Max Act: 7.6495. Min Act: -0.1700
Data Index: 3748383 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9620. Min Range: -7.9620
Max Act: 7.6495. Min Act: -0.1700
Data Index: 4730064 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9620. Min Range: -7.9620
Max Act: 7.6183. Min Act: -0.1700
Data Index: 121778 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9620. Min Range: -7.9620
Max Act: 7.5870. Min Act: -0.1700
Data Index: 1027676 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9620. Min Range: -7.9620
Max Act: 7.5558. Min Act: -0.1700
Data Index: 4020334 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9620. Min Range: -7.9620
Max Act: 7.5870. Min Act: -0.1700
Data Index: 59042 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9620. Min Range: -7.9620
Max Act: 7.5558. Min Act: -0.1700
Data Index: 8175955 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9620. Min Range: -7.9620
Max Act: 7.5245. Min Act: -0.1700
Data Index: 3491678 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9620. Min Range: -7.9620
Max Act: 7.5245. Min Act: -0.1700
Data Index: 5680342 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #19