Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3294 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.4010. Min Range: -10.4010
Max Act: 10.4010. Min Act: -0.1700
Data Index: 639890 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.4010. Min Range: -10.4010
Max Act: 10.3385. Min Act: -0.1700
Data Index: 3845699 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.4010. Min Range: -10.4010
Max Act: 10.3385. Min Act: -0.1700
Data Index: 1207288 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.4010. Min Range: -10.4010
Max Act: 10.2135. Min Act: -0.1700
Data Index: 6110182 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.4010. Min Range: -10.4010
Max Act: 10.2135. Min Act: -0.1700
Data Index: 5520401 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.4010. Min Range: -10.4010
Max Act: 10.2135. Min Act: -0.1700
Data Index: 5543232 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.4010. Min Range: -10.4010
Max Act: 10.1510. Min Act: -0.1700
Data Index: 3753683 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.4010. Min Range: -10.4010
Max Act: 10.1510. Min Act: -0.1700
Data Index: 6222680 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.4010. Min Range: -10.4010
Max Act: 10.0260. Min Act: -0.1700
Data Index: 5061258 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.4010. Min Range: -10.4010
Max Act: 10.0885. Min Act: -0.1700
Data Index: 3636104 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.4010. Min Range: -10.4010
Max Act: 10.0260. Min Act: -0.1700
Data Index: 6491390 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.4010. Min Range: -10.4010
Max Act: 10.0260. Min Act: -0.1700
Data Index: 2224560 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.4010. Min Range: -10.4010
Max Act: 10.0260. Min Act: -0.1700
Data Index: 1150436 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.4010. Min Range: -10.4010
Max Act: 9.9635. Min Act: -0.1700
Data Index: 4352716 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.4010. Min Range: -10.4010
Max Act: 9.8385. Min Act: -0.1700
Data Index: 2310697 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.4010. Min Range: -10.4010
Max Act: 9.9010. Min Act: -0.1700
Data Index: 423056 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.4010. Min Range: -10.4010
Max Act: 9.9010. Min Act: -0.1700
Data Index: 7030753 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.4010. Min Range: -10.4010
Max Act: 9.9010. Min Act: -0.1700
Data Index: 2200670 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.4010. Min Range: -10.4010
Max Act: 9.9010. Min Act: -0.1700
Data Index: 4109096 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.4010. Min Range: -10.4010
Max Act: 9.8385. Min Act: -0.1700
Data Index: 2380422 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #19