Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2045 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3122. Min Range: -6.3122
Max Act: 6.3122. Min Act: -0.1700
Data Index: 536878 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3122. Min Range: -6.3122
Max Act: 6.2497. Min Act: -0.1700
Data Index: 7535011 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3122. Min Range: -6.3122
Max Act: 6.2185. Min Act: -0.1700
Data Index: 4268806 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3122. Min Range: -6.3122
Max Act: 6.2185. Min Act: -0.1700
Data Index: 6377051 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3122. Min Range: -6.3122
Max Act: 6.1872. Min Act: -0.1700
Data Index: 8025039 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3122. Min Range: -6.3122
Max Act: 6.1560. Min Act: -0.1700
Data Index: 5408395 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3122. Min Range: -6.3122
Max Act: 6.0935. Min Act: -0.1700
Data Index: 1822966 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3122. Min Range: -6.3122
Max Act: 6.1560. Min Act: -0.1700
Data Index: 1559361 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3122. Min Range: -6.3122
Max Act: 6.0935. Min Act: -0.1700
Data Index: 4668161 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3122. Min Range: -6.3122
Max Act: 6.0622. Min Act: -0.1700
Data Index: 4135971 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3122. Min Range: -6.3122
Max Act: 6.0622. Min Act: -0.1700
Data Index: 6815526 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3122. Min Range: -6.3122
Max Act: 6.0622. Min Act: -0.1700
Data Index: 3038146 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3122. Min Range: -6.3122
Max Act: 6.0622. Min Act: -0.1700
Data Index: 1427287 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3122. Min Range: -6.3122
Max Act: 6.0310. Min Act: -0.1700
Data Index: 837196 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3122. Min Range: -6.3122
Max Act: 6.0310. Min Act: -0.1700
Data Index: 5284442 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3122. Min Range: -6.3122
Max Act: 6.0622. Min Act: -0.1700
Data Index: 7917697 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3122. Min Range: -6.3122
Max Act: 6.0310. Min Act: -0.1700
Data Index: 4976731 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3122. Min Range: -6.3122
Max Act: 6.0310. Min Act: -0.1700
Data Index: 2640269 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3122. Min Range: -6.3122
Max Act: 6.0310. Min Act: -0.1700
Data Index: 2275815 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3122. Min Range: -6.3122
Max Act: 6.0310. Min Act: -0.1700
Data Index: 1700148 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #19