Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4601 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6043. Min Range: -5.6043
Max Act: 5.6043. Min Act: -0.1700
Data Index: 6531168 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6043. Min Range: -5.6043
Max Act: 5.6043. Min Act: -0.1700
Data Index: 6588815 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6043. Min Range: -5.6043
Max Act: 5.3231. Min Act: -0.1700
Data Index: 2166670 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6043. Min Range: -5.6043
Max Act: 5.2918. Min Act: -0.1700
Data Index: 459883 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6043. Min Range: -5.6043
Max Act: 5.0731. Min Act: -0.1700
Data Index: 537497 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6043. Min Range: -5.6043
Max Act: 5.0418. Min Act: -0.1700
Data Index: 459880 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6043. Min Range: -5.6043
Max Act: 5.0106. Min Act: -0.1699
Data Index: 5975439 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6043. Min Range: -5.6043
Max Act: 4.9793. Min Act: -0.1700
Data Index: 6349089 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6043. Min Range: -5.6043
Max Act: 4.9481. Min Act: -0.1700
Data Index: 6349088 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6043. Min Range: -5.6043
Max Act: 4.9481. Min Act: -0.1700
Data Index: 2281914 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6043. Min Range: -5.6043
Max Act: 4.8856. Min Act: -0.1700
Data Index: 1200909 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6043. Min Range: -5.6043
Max Act: 4.8856. Min Act: -0.1700
Data Index: 4979192 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6043. Min Range: -5.6043
Max Act: 4.9168. Min Act: -0.1700
Data Index: 6410896 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6043. Min Range: -5.6043
Max Act: 4.8543. Min Act: -0.1700
Data Index: 7523765 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6043. Min Range: -5.6043
Max Act: 4.8543. Min Act: -0.1700
Data Index: 4188247 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6043. Min Range: -5.6043
Max Act: 4.8543. Min Act: -0.1700
Data Index: 4188244 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6043. Min Range: -5.6043
Max Act: 4.8543. Min Act: -0.1700
Data Index: 4188262 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6043. Min Range: -5.6043
Max Act: 4.8231. Min Act: -0.1700
Data Index: 4188267 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6043. Min Range: -5.6043
Max Act: 4.7918. Min Act: -0.1700
Data Index: 953379 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6043. Min Range: -5.6043
Max Act: 4.8231. Min Act: -0.1700
Data Index: 4188255 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #19