Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3453 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3244. Min Range: -6.3244
Max Act: 6.3244. Min Act: -0.1700
Data Index: 1380716 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3244. Min Range: -6.3244
Max Act: 6.2932. Min Act: -0.1700
Data Index: 8713524 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3244. Min Range: -6.3244
Max Act: 6.1994. Min Act: -0.1700
Data Index: 2748444 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3244. Min Range: -6.3244
Max Act: 6.0119. Min Act: -0.1700
Data Index: 2123221 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3244. Min Range: -6.3244
Max Act: 6.0119. Min Act: -0.1700
Data Index: 405235 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3244. Min Range: -6.3244
Max Act: 6.0119. Min Act: -0.1700
Data Index: 3933367 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3244. Min Range: -6.3244
Max Act: 5.9807. Min Act: -0.1700
Data Index: 5139601 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3244. Min Range: -6.3244
Max Act: 5.9494. Min Act: -0.1700
Data Index: 8152790 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3244. Min Range: -6.3244
Max Act: 5.9494. Min Act: -0.1700
Data Index: 6685695 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3244. Min Range: -6.3244
Max Act: 5.9807. Min Act: -0.1700
Data Index: 138845 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3244. Min Range: -6.3244
Max Act: 5.9182. Min Act: -0.1700
Data Index: 7204030 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3244. Min Range: -6.3244
Max Act: 5.8869. Min Act: -0.1700
Data Index: 2783654 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3244. Min Range: -6.3244
Max Act: 5.8869. Min Act: -0.1700
Data Index: 5831349 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3244. Min Range: -6.3244
Max Act: 5.8557. Min Act: -0.1700
Data Index: 5948533 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3244. Min Range: -6.3244
Max Act: 5.7932. Min Act: -0.1700
Data Index: 6378860 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3244. Min Range: -6.3244
Max Act: 5.8557. Min Act: -0.1700
Data Index: 2841171 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3244. Min Range: -6.3244
Max Act: 5.8244. Min Act: -0.1700
Data Index: 8631987 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3244. Min Range: -6.3244
Max Act: 5.7932. Min Act: -0.1700
Data Index: 4503310 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3244. Min Range: -6.3244
Max Act: 5.7619. Min Act: -0.1700
Data Index: 6581635 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3244. Min Range: -6.3244
Max Act: 5.7619. Min Act: -0.1700
Data Index: 5721804 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #19