Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3226 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6067. Min Range: -3.6067
Max Act: 3.6067. Min Act: -0.1700
Data Index: 8305033 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6067. Min Range: -3.6067
Max Act: 3.6067. Min Act: -0.1700
Data Index: 939115 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6067. Min Range: -3.6067
Max Act: 3.5128. Min Act: -0.1700
Data Index: 8541250 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6067. Min Range: -3.6067
Max Act: 3.4971. Min Act: -0.1700
Data Index: 8658991 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6067. Min Range: -3.6067
Max Act: 3.4815. Min Act: -0.1700
Data Index: 6081700 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6067. Min Range: -3.6067
Max Act: 3.4658. Min Act: -0.1700
Data Index: 4566093 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6067. Min Range: -3.6067
Max Act: 3.4345. Min Act: -0.1700
Data Index: 6829537 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6067. Min Range: -3.6067
Max Act: 3.4345. Min Act: -0.1700
Data Index: 3905719 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6067. Min Range: -3.6067
Max Act: 3.4188. Min Act: -0.1700
Data Index: 7470483 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6067. Min Range: -3.6067
Max Act: 3.3874. Min Act: -0.1700
Data Index: 2227552 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6067. Min Range: -3.6067
Max Act: 3.3874. Min Act: -0.1700
Data Index: 5150185 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6067. Min Range: -3.6067
Max Act: 3.3874. Min Act: -0.1700
Data Index: 2377677 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6067. Min Range: -3.6067
Max Act: 3.3718. Min Act: -0.1700
Data Index: 2818520 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6067. Min Range: -3.6067
Max Act: 3.3718. Min Act: -0.1700
Data Index: 33998 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6067. Min Range: -3.6067
Max Act: 3.3718. Min Act: -0.1700
Data Index: 3541074 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6067. Min Range: -3.6067
Max Act: 3.3404. Min Act: -0.1700
Data Index: 2443072 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6067. Min Range: -3.6067
Max Act: 3.3404. Min Act: -0.1700
Data Index: 6860005 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6067. Min Range: -3.6067
Max Act: 3.3247. Min Act: -0.1700
Data Index: 5241082 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6067. Min Range: -3.6067
Max Act: 3.3090. Min Act: -0.1700
Data Index: 3993918 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6067. Min Range: -3.6067
Max Act: 3.3247. Min Act: -0.1700
Data Index: 4794962 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #19