Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3225 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0392. Min Range: -7.0392
Max Act: 7.0392. Min Act: -0.1700
Data Index: 5412545 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0392. Min Range: -7.0392
Max Act: 6.6017. Min Act: -0.1700
Data Index: 6130246 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0392. Min Range: -7.0392
Max Act: 6.4767. Min Act: -0.1700
Data Index: 2138591 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0392. Min Range: -7.0392
Max Act: 6.4455. Min Act: -0.1700
Data Index: 4366559 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0392. Min Range: -7.0392
Max Act: 6.4455. Min Act: -0.1700
Data Index: 8471167 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0392. Min Range: -7.0392
Max Act: 6.3830. Min Act: -0.1700
Data Index: 2240884 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0392. Min Range: -7.0392
Max Act: 6.3517. Min Act: -0.1700
Data Index: 4801148 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0392. Min Range: -7.0392
Max Act: 6.3205. Min Act: -0.1700
Data Index: 7955270 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0392. Min Range: -7.0392
Max Act: 6.3205. Min Act: -0.1700
Data Index: 583991 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0392. Min Range: -7.0392
Max Act: 6.2892. Min Act: -0.1700
Data Index: 5446226 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0392. Min Range: -7.0392
Max Act: 6.2267. Min Act: -0.1700
Data Index: 2338092 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0392. Min Range: -7.0392
Max Act: 6.2267. Min Act: -0.1700
Data Index: 5730192 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0392. Min Range: -7.0392
Max Act: 6.1955. Min Act: -0.1700
Data Index: 4236738 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0392. Min Range: -7.0392
Max Act: 6.1955. Min Act: -0.1700
Data Index: 1012594 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0392. Min Range: -7.0392
Max Act: 6.1955. Min Act: -0.1700
Data Index: 1233642 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0392. Min Range: -7.0392
Max Act: 6.1955. Min Act: -0.1700
Data Index: 2400166 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0392. Min Range: -7.0392
Max Act: 6.1955. Min Act: -0.1700
Data Index: 4471376 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0392. Min Range: -7.0392
Max Act: 6.1330. Min Act: -0.1700
Data Index: 6633991 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0392. Min Range: -7.0392
Max Act: 6.1330. Min Act: -0.1700
Data Index: 8275816 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0392. Min Range: -7.0392
Max Act: 6.1017. Min Act: -0.1700
Data Index: 6813348 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #19