Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3130 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.2520. Min Range: -10.2520
Max Act: 10.2520. Min Act: -0.1700
Data Index: 4671254 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2520. Min Range: -10.2520
Max Act: 10.1895. Min Act: -0.1700
Data Index: 4671255 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2520. Min Range: -10.2520
Max Act: 9.9395. Min Act: -0.1700
Data Index: 3517545 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2520. Min Range: -10.2520
Max Act: 9.8145. Min Act: -0.1700
Data Index: 1250043 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2520. Min Range: -10.2520
Max Act: 9.8145. Min Act: -0.1700
Data Index: 5437011 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2520. Min Range: -10.2520
Max Act: 9.8145. Min Act: -0.1700
Data Index: 8665617 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2520. Min Range: -10.2520
Max Act: 9.8145. Min Act: -0.1700
Data Index: 7766337 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2520. Min Range: -10.2520
Max Act: 9.7520. Min Act: -0.1700
Data Index: 6592209 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2520. Min Range: -10.2520
Max Act: 9.6895. Min Act: -0.1700
Data Index: 7380361 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2520. Min Range: -10.2520
Max Act: 9.6895. Min Act: -0.1700
Data Index: 528097 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2520. Min Range: -10.2520
Max Act: 9.6895. Min Act: -0.1700
Data Index: 6455046 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2520. Min Range: -10.2520
Max Act: 9.6270. Min Act: -0.1700
Data Index: 5081723 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2520. Min Range: -10.2520
Max Act: 9.5645. Min Act: -0.1700
Data Index: 4937380 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2520. Min Range: -10.2520
Max Act: 9.6270. Min Act: -0.1700
Data Index: 1780741 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2520. Min Range: -10.2520
Max Act: 9.5645. Min Act: -0.1700
Data Index: 2850629 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2520. Min Range: -10.2520
Max Act: 9.6270. Min Act: -0.1700
Data Index: 8809190 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2520. Min Range: -10.2520
Max Act: 9.5645. Min Act: -0.1700
Data Index: 6782788 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2520. Min Range: -10.2520
Max Act: 9.5020. Min Act: -0.1700
Data Index: 3517546 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2520. Min Range: -10.2520
Max Act: 9.5645. Min Act: -0.1700
Data Index: 8425738 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2520. Min Range: -10.2520
Max Act: 9.5020. Min Act: -0.1700
Data Index: 3043838 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #19