Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3280 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.4936. Min Range: -0.4936
Max Act: 0.4936. Min Act: -0.1700
Data Index: 383802 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.4936. Min Range: -0.4936
Max Act: 0.4420. Min Act: -0.1700
Data Index: 695924 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.4936. Min Range: -0.4936
Max Act: 0.4347. Min Act: -0.1699
Data Index: 8831674 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.4936. Min Range: -0.4936
Max Act: 0.4275. Min Act: -0.1700
Data Index: 5014107 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.4936. Min Range: -0.4936
Max Act: 0.4347. Min Act: -0.1700
Data Index: 1401809 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.4936. Min Range: -0.4936
Max Act: 0.4203. Min Act: -0.1700
Data Index: 6110501 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.4936. Min Range: -0.4936
Max Act: 0.4203. Min Act: -0.1700
Data Index: 2477545 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.4936. Min Range: -0.4936
Max Act: 0.4132. Min Act: -0.1700
Data Index: 8795284 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.4936. Min Range: -0.4936
Max Act: 0.4132. Min Act: -0.1700
Data Index: 3463258 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.4936. Min Range: -0.4936
Max Act: 0.4132. Min Act: -0.1700
Data Index: 2081115 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.4936. Min Range: -0.4936
Max Act: 0.4132. Min Act: -0.1700
Data Index: 2862497 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.4936. Min Range: -0.4936
Max Act: 0.4061. Min Act: -0.1700
Data Index: 3285870 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.4936. Min Range: -0.4936
Max Act: 0.4061. Min Act: -0.1684
Data Index: 3973780 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.4936. Min Range: -0.4936
Max Act: 0.3920. Min Act: -0.1700
Data Index: 6875159 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.4936. Min Range: -0.4936
Max Act: 0.3920. Min Act: -0.1700
Data Index: 8434193 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.4936. Min Range: -0.4936
Max Act: 0.3850. Min Act: -0.1699
Data Index: 3896424 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.4936. Min Range: -0.4936
Max Act: 0.3850. Min Act: -0.1700
Data Index: 6457404 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.4936. Min Range: -0.4936
Max Act: 0.3850. Min Act: -0.1680
Data Index: 6295983 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.4936. Min Range: -0.4936
Max Act: 0.3711. Min Act: -0.1699
Data Index: 1650033 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.4936. Min Range: -0.4936
Max Act: 0.3780. Min Act: -0.1700
Data Index: 5994190 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #19