Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3279 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2050. Min Range: -5.2050
Max Act: 5.2050. Min Act: -0.1700
Data Index: 2704616 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2050. Min Range: -5.2050
Max Act: 5.2050. Min Act: -0.1700
Data Index: 425591 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2050. Min Range: -5.2050
Max Act: 5.0800. Min Act: -0.1700
Data Index: 278879 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2050. Min Range: -5.2050
Max Act: 5.1112. Min Act: -0.1700
Data Index: 5018141 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2050. Min Range: -5.2050
Max Act: 5.0487. Min Act: -0.1700
Data Index: 8803020 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2050. Min Range: -5.2050
Max Act: 5.0487. Min Act: -0.1700
Data Index: 6140738 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2050. Min Range: -5.2050
Max Act: 5.0487. Min Act: -0.1700
Data Index: 1223651 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2050. Min Range: -5.2050
Max Act: 5.0175. Min Act: -0.1700
Data Index: 2381501 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2050. Min Range: -5.2050
Max Act: 5.0175. Min Act: -0.1700
Data Index: 7231505 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2050. Min Range: -5.2050
Max Act: 5.0175. Min Act: -0.1700
Data Index: 4812419 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2050. Min Range: -5.2050
Max Act: 5.0175. Min Act: -0.1700
Data Index: 1404897 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2050. Min Range: -5.2050
Max Act: 4.9862. Min Act: -0.1700
Data Index: 7829246 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2050. Min Range: -5.2050
Max Act: 4.9862. Min Act: -0.1700
Data Index: 4042502 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2050. Min Range: -5.2050
Max Act: 4.9862. Min Act: -0.1700
Data Index: 2069500 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2050. Min Range: -5.2050
Max Act: 4.9862. Min Act: -0.1700
Data Index: 6399750 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2050. Min Range: -5.2050
Max Act: 4.9550. Min Act: -0.1700
Data Index: 6608488 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2050. Min Range: -5.2050
Max Act: 4.9862. Min Act: -0.1700
Data Index: 1156310 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2050. Min Range: -5.2050
Max Act: 4.9862. Min Act: -0.1700
Data Index: 3854425 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2050. Min Range: -5.2050
Max Act: 4.9862. Min Act: -0.1700
Data Index: 4879418 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2050. Min Range: -5.2050
Max Act: 4.9862. Min Act: -0.1700
Data Index: 3785277 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #19