Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3275 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0704. Min Range: -7.0704
Max Act: 7.0704. Min Act: -0.1698
Data Index: 1812560 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0704. Min Range: -7.0704
Max Act: 7.0392. Min Act: -0.1700
Data Index: 268410 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0704. Min Range: -7.0704
Max Act: 7.0392. Min Act: -0.1700
Data Index: 2004089 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0704. Min Range: -7.0704
Max Act: 6.9454. Min Act: -0.1700
Data Index: 3874854 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0704. Min Range: -7.0704
Max Act: 6.9142. Min Act: -0.1700
Data Index: 16076 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0704. Min Range: -7.0704
Max Act: 6.7892. Min Act: -0.1700
Data Index: 8301257 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0704. Min Range: -7.0704
Max Act: 6.7579. Min Act: -0.1700
Data Index: 7984706 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0704. Min Range: -7.0704
Max Act: 6.7579. Min Act: -0.1700
Data Index: 7930352 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0704. Min Range: -7.0704
Max Act: 6.7267. Min Act: -0.1700
Data Index: 7313030 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0704. Min Range: -7.0704
Max Act: 6.6329. Min Act: -0.1700
Data Index: 6090186 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0704. Min Range: -7.0704
Max Act: 6.6329. Min Act: -0.1700
Data Index: 6721205 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0704. Min Range: -7.0704
Max Act: 6.6017. Min Act: -0.1700
Data Index: 6468977 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0704. Min Range: -7.0704
Max Act: 6.6017. Min Act: -0.1700
Data Index: 4925762 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0704. Min Range: -7.0704
Max Act: 6.6017. Min Act: -0.1700
Data Index: 1878206 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0704. Min Range: -7.0704
Max Act: 6.6017. Min Act: -0.1700
Data Index: 8573460 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0704. Min Range: -7.0704
Max Act: 6.6329. Min Act: -0.1700
Data Index: 3025666 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0704. Min Range: -7.0704
Max Act: 6.6017. Min Act: -0.1700
Data Index: 43320 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0704. Min Range: -7.0704
Max Act: 6.5704. Min Act: -0.1700
Data Index: 5683571 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0704. Min Range: -7.0704
Max Act: 6.5704. Min Act: -0.1700
Data Index: 1996351 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0704. Min Range: -7.0704
Max Act: 6.5079. Min Act: -0.1700
Data Index: 798873 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #19