Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3862 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.7543. Min Act: -0.1700
Data Index: 7265356 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.6293. Min Act: -0.1700
Data Index: 4048699 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.3168. Min Act: -0.1700
Data Index: 6243751 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.3168. Min Act: -0.1700
Data Index: 2179888 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.2855. Min Act: -0.1700
Data Index: 4451848 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.2543. Min Act: -0.1700
Data Index: 2698265 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.1605. Min Act: -0.1700
Data Index: 8457041 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.1605. Min Act: -0.1700
Data Index: 7220 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.1605. Min Act: -0.1700
Data Index: 2677791 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.1605. Min Act: -0.1700
Data Index: 3652381 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.1293. Min Act: -0.1700
Data Index: 4081094 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.1293. Min Act: -0.1700
Data Index: 4574107 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.0668. Min Act: -0.1700
Data Index: 4443999 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.0980. Min Act: -0.1700
Data Index: 7798542 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.0668. Min Act: -0.1700
Data Index: 574986 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.0355. Min Act: -0.1700
Data Index: 6457401 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.0355. Min Act: -0.1700
Data Index: 8187966 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.0355. Min Act: -0.1700
Data Index: 672059 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.0355. Min Act: -0.1700
Data Index: 6959038 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.0043. Min Act: -0.1700
Data Index: 8029314 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #19