Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2196 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6059. Min Range: -5.6059
Max Act: 5.6059. Min Act: -0.1700
Data Index: 49502 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6059. Min Range: -5.6059
Max Act: 5.3872. Min Act: -0.1700
Data Index: 4543746 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6059. Min Range: -5.6059
Max Act: 5.2309. Min Act: -0.1700
Data Index: 7068078 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6059. Min Range: -5.6059
Max Act: 5.2622. Min Act: -0.1700
Data Index: 5172440 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6059. Min Range: -5.6059
Max Act: 5.1997. Min Act: -0.1700
Data Index: 2504167 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6059. Min Range: -5.6059
Max Act: 5.1997. Min Act: -0.1700
Data Index: 7735005 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6059. Min Range: -5.6059
Max Act: 5.1684. Min Act: -0.1700
Data Index: 947545 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6059. Min Range: -5.6059
Max Act: 5.1997. Min Act: -0.1700
Data Index: 2244202 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6059. Min Range: -5.6059
Max Act: 5.1684. Min Act: -0.1700
Data Index: 2878938 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6059. Min Range: -5.6059
Max Act: 5.1684. Min Act: -0.1700
Data Index: 5821025 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6059. Min Range: -5.6059
Max Act: 5.1997. Min Act: -0.1700
Data Index: 5458954 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6059. Min Range: -5.6059
Max Act: 5.1372. Min Act: -0.1700
Data Index: 715233 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6059. Min Range: -5.6059
Max Act: 5.1059. Min Act: -0.1700
Data Index: 3907406 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6059. Min Range: -5.6059
Max Act: 5.1372. Min Act: -0.1700
Data Index: 2825072 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6059. Min Range: -5.6059
Max Act: 5.1372. Min Act: -0.1700
Data Index: 4722996 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6059. Min Range: -5.6059
Max Act: 5.1059. Min Act: -0.1700
Data Index: 4161248 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6059. Min Range: -5.6059
Max Act: 5.1059. Min Act: -0.1700
Data Index: 1545806 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6059. Min Range: -5.6059
Max Act: 5.0747. Min Act: -0.1700
Data Index: 5763122 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6059. Min Range: -5.6059
Max Act: 5.1059. Min Act: -0.1700
Data Index: 2504168 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6059. Min Range: -5.6059
Max Act: 5.1372. Min Act: -0.1700
Data Index: 8325777 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #19