Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3582 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.2049. Min Range: -10.2049
Max Act: 10.1424. Min Act: -0.1700
Data Index: 3584139 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2049. Min Range: -10.2049
Max Act: 10.0799. Min Act: -0.1700
Data Index: 5311763 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2049. Min Range: -10.2049
Max Act: 10.2049. Min Act: -0.1700
Data Index: 3770854 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2049. Min Range: -10.2049
Max Act: 10.0799. Min Act: -0.1700
Data Index: 1797413 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2049. Min Range: -10.2049
Max Act: 10.0799. Min Act: -0.1700
Data Index: 5475770 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2049. Min Range: -10.2049
Max Act: 10.0174. Min Act: -0.1700
Data Index: 3290321 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2049. Min Range: -10.2049
Max Act: 10.0799. Min Act: -0.1700
Data Index: 7074678 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2049. Min Range: -10.2049
Max Act: 10.0174. Min Act: -0.1699
Data Index: 6180069 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2049. Min Range: -10.2049
Max Act: 10.0174. Min Act: -0.1700
Data Index: 269252 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2049. Min Range: -10.2049
Max Act: 9.9549. Min Act: -0.1700
Data Index: 6824606 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2049. Min Range: -10.2049
Max Act: 10.0174. Min Act: -0.1700
Data Index: 5511737 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2049. Min Range: -10.2049
Max Act: 9.9549. Min Act: -0.1700
Data Index: 7582547 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2049. Min Range: -10.2049
Max Act: 9.9549. Min Act: -0.1700
Data Index: 6937713 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2049. Min Range: -10.2049
Max Act: 9.9549. Min Act: -0.1700
Data Index: 1675194 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2049. Min Range: -10.2049
Max Act: 9.8924. Min Act: -0.1700
Data Index: 3000582 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2049. Min Range: -10.2049
Max Act: 9.8924. Min Act: -0.1700
Data Index: 271139 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2049. Min Range: -10.2049
Max Act: 9.8299. Min Act: -0.1700
Data Index: 690944 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2049. Min Range: -10.2049
Max Act: 9.8299. Min Act: -0.1700
Data Index: 253450 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2049. Min Range: -10.2049
Max Act: 9.8924. Min Act: -0.1700
Data Index: 3426012 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2049. Min Range: -10.2049
Max Act: 9.8924. Min Act: -0.1700
Data Index: 6348800 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #19