Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3356 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6620. Min Range: -7.6620
Max Act: 7.6620. Min Act: -0.1700
Data Index: 1196080 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6620. Min Range: -7.6620
Max Act: 7.3495. Min Act: -0.1700
Data Index: 5778781 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6620. Min Range: -7.6620
Max Act: 7.2870. Min Act: -0.1700
Data Index: 4836931 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6620. Min Range: -7.6620
Max Act: 7.2557. Min Act: -0.1700
Data Index: 1147228 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6620. Min Range: -7.6620
Max Act: 7.2245. Min Act: -0.1700
Data Index: 3655355 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6620. Min Range: -7.6620
Max Act: 7.1620. Min Act: -0.1700
Data Index: 1299190 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6620. Min Range: -7.6620
Max Act: 7.1620. Min Act: -0.1700
Data Index: 4687229 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6620. Min Range: -7.6620
Max Act: 7.1620. Min Act: -0.1700
Data Index: 252344 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6620. Min Range: -7.6620
Max Act: 7.1307. Min Act: -0.1700
Data Index: 7032815 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6620. Min Range: -7.6620
Max Act: 7.1307. Min Act: -0.1700
Data Index: 6405515 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6620. Min Range: -7.6620
Max Act: 7.1307. Min Act: -0.1700
Data Index: 8015423 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6620. Min Range: -7.6620
Max Act: 7.0682. Min Act: -0.1700
Data Index: 3610398 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6620. Min Range: -7.6620
Max Act: 7.0682. Min Act: -0.1700
Data Index: 2444256 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6620. Min Range: -7.6620
Max Act: 7.0370. Min Act: -0.1700
Data Index: 5757874 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6620. Min Range: -7.6620
Max Act: 7.0370. Min Act: -0.1700
Data Index: 3480176 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6620. Min Range: -7.6620
Max Act: 7.0057. Min Act: -0.1700
Data Index: 1701578 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6620. Min Range: -7.6620
Max Act: 7.0057. Min Act: -0.1700
Data Index: 6649773 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6620. Min Range: -7.6620
Max Act: 7.0370. Min Act: -0.1700
Data Index: 4869918 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6620. Min Range: -7.6620
Max Act: 7.0057. Min Act: -0.1700
Data Index: 8367665 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6620. Min Range: -7.6620
Max Act: 7.0057. Min Act: -0.1700
Data Index: 16276 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #19