Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3771 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1290. Min Range: -4.1290
Max Act: 4.1290. Min Act: -0.1700
Data Index: 3502390 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1290. Min Range: -4.1290
Max Act: 4.0040. Min Act: -0.1700
Data Index: 2460340 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1290. Min Range: -4.1290
Max Act: 3.9727. Min Act: -0.1700
Data Index: 4241395 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1290. Min Range: -4.1290
Max Act: 3.9727. Min Act: -0.1700
Data Index: 6306960 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1290. Min Range: -4.1290
Max Act: 3.9727. Min Act: -0.1700
Data Index: 614255 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1290. Min Range: -4.1290
Max Act: 3.9727. Min Act: -0.1700
Data Index: 5156347 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1290. Min Range: -4.1290
Max Act: 3.9571. Min Act: -0.1700
Data Index: 7291372 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1290. Min Range: -4.1290
Max Act: 3.9258. Min Act: -0.1700
Data Index: 3503446 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1290. Min Range: -4.1290
Max Act: 3.9571. Min Act: -0.1700
Data Index: 2086469 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1290. Min Range: -4.1290
Max Act: 3.9102. Min Act: -0.1700
Data Index: 7689946 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1290. Min Range: -4.1290
Max Act: 3.9258. Min Act: -0.1700
Data Index: 6219430 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1290. Min Range: -4.1290
Max Act: 3.9415. Min Act: -0.1700
Data Index: 4652786 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1290. Min Range: -4.1290
Max Act: 3.9258. Min Act: -0.1700
Data Index: 7433816 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1290. Min Range: -4.1290
Max Act: 3.9258. Min Act: -0.1700
Data Index: 7689942 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1290. Min Range: -4.1290
Max Act: 3.9102. Min Act: -0.1700
Data Index: 866153 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1290. Min Range: -4.1290
Max Act: 3.9258. Min Act: -0.1700
Data Index: 3417631 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1290. Min Range: -4.1290
Max Act: 3.9102. Min Act: -0.1700
Data Index: 280554 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1290. Min Range: -4.1290
Max Act: 3.8946. Min Act: -0.1700
Data Index: 2580594 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1290. Min Range: -4.1290
Max Act: 3.8946. Min Act: -0.1700
Data Index: 4138755 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1290. Min Range: -4.1290
Max Act: 3.8946. Min Act: -0.1700
Data Index: 2756385 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19