Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3933 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1926. Min Range: -5.1926
Max Act: 5.1926. Min Act: -0.1700
Data Index: 2405598 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1926. Min Range: -5.1926
Max Act: 5.0988. Min Act: -0.1700
Data Index: 2117105 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1926. Min Range: -5.1926
Max Act: 5.1301. Min Act: -0.1700
Data Index: 7733211 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1926. Min Range: -5.1926
Max Act: 5.0988. Min Act: -0.1700
Data Index: 751123 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1926. Min Range: -5.1926
Max Act: 5.0363. Min Act: -0.1700
Data Index: 4233092 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1926. Min Range: -5.1926
Max Act: 5.0363. Min Act: -0.1700
Data Index: 6798897 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1926. Min Range: -5.1926
Max Act: 5.0363. Min Act: -0.1700
Data Index: 2405600 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1926. Min Range: -5.1926
Max Act: 5.0051. Min Act: -0.1700
Data Index: 152252 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1926. Min Range: -5.1926
Max Act: 5.0051. Min Act: -0.1700
Data Index: 4398707 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1926. Min Range: -5.1926
Max Act: 5.0051. Min Act: -0.1700
Data Index: 1090878 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1926. Min Range: -5.1926
Max Act: 4.9738. Min Act: -0.1700
Data Index: 3569191 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1926. Min Range: -5.1926
Max Act: 5.0051. Min Act: -0.1700
Data Index: 3431039 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1926. Min Range: -5.1926
Max Act: 4.9738. Min Act: -0.1700
Data Index: 1436654 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1926. Min Range: -5.1926
Max Act: 4.9738. Min Act: -0.1700
Data Index: 8784510 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1926. Min Range: -5.1926
Max Act: 4.9426. Min Act: -0.1700
Data Index: 5195514 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1926. Min Range: -5.1926
Max Act: 4.9738. Min Act: -0.1700
Data Index: 5404325 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1926. Min Range: -5.1926
Max Act: 4.9113. Min Act: -0.1700
Data Index: 2517490 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1926. Min Range: -5.1926
Max Act: 4.9426. Min Act: -0.1700
Data Index: 6849506 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1926. Min Range: -5.1926
Max Act: 4.9113. Min Act: -0.1700
Data Index: 200994 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1926. Min Range: -5.1926
Max Act: 4.9113. Min Act: -0.1700
Data Index: 5393652 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #19