Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3493 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 13.0425. Min Range: -13.0425
Max Act: 13.0425. Min Act: -0.1700
Data Index: 1681032 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.0425. Min Range: -13.0425
Max Act: 12.6675. Min Act: -0.1700
Data Index: 7307596 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.0425. Min Range: -13.0425
Max Act: 12.3550. Min Act: -0.1700
Data Index: 7772943 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.0425. Min Range: -13.0425
Max Act: 12.1050. Min Act: -0.1700
Data Index: 605627 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.0425. Min Range: -13.0425
Max Act: 12.0425. Min Act: -0.1700
Data Index: 4849003 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.0425. Min Range: -13.0425
Max Act: 11.9175. Min Act: -0.1700
Data Index: 4818956 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.0425. Min Range: -13.0425
Max Act: 11.9175. Min Act: -0.1700
Data Index: 6905475 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.0425. Min Range: -13.0425
Max Act: 11.8550. Min Act: -0.1700
Data Index: 6188697 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.0425. Min Range: -13.0425
Max Act: 11.9175. Min Act: -0.1700
Data Index: 5457193 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.0425. Min Range: -13.0425
Max Act: 11.8550. Min Act: -0.1700
Data Index: 174506 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.0425. Min Range: -13.0425
Max Act: 11.7300. Min Act: -0.1700
Data Index: 6954719 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.0425. Min Range: -13.0425
Max Act: 11.7300. Min Act: -0.1700
Data Index: 303849 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.0425. Min Range: -13.0425
Max Act: 11.6050. Min Act: -0.1700
Data Index: 7236834 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.0425. Min Range: -13.0425
Max Act: 11.5425. Min Act: -0.1700
Data Index: 2388017 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.0425. Min Range: -13.0425
Max Act: 11.5425. Min Act: -0.1700
Data Index: 2978662 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.0425. Min Range: -13.0425
Max Act: 11.5425. Min Act: -0.1700
Data Index: 3297986 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.0425. Min Range: -13.0425
Max Act: 11.6050. Min Act: -0.1700
Data Index: 5242308 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.0425. Min Range: -13.0425
Max Act: 11.5425. Min Act: -0.1700
Data Index: 423919 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.0425. Min Range: -13.0425
Max Act: 11.5425. Min Act: -0.1700
Data Index: 7677786 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.0425. Min Range: -13.0425
Max Act: 11.5425. Min Act: -0.1700
Data Index: 1768056 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #19