Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2740 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7998. Min Range: -5.7998
Max Act: 5.7998. Min Act: -0.1700
Data Index: 4708249 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7998. Min Range: -5.7998
Max Act: 5.7373. Min Act: -0.1700
Data Index: 692898 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7998. Min Range: -5.7998
Max Act: 5.7685. Min Act: -0.1700
Data Index: 1864343 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7998. Min Range: -5.7998
Max Act: 5.7373. Min Act: -0.1700
Data Index: 7701469 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7998. Min Range: -5.7998
Max Act: 5.7060. Min Act: -0.1700
Data Index: 2783676 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7998. Min Range: -5.7998
Max Act: 5.7060. Min Act: -0.1700
Data Index: 1129651 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7998. Min Range: -5.7998
Max Act: 5.7060. Min Act: -0.1700
Data Index: 357586 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7998. Min Range: -5.7998
Max Act: 5.6435. Min Act: -0.1700
Data Index: 5666580 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7998. Min Range: -5.7998
Max Act: 5.6123. Min Act: -0.1700
Data Index: 526365 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7998. Min Range: -5.7998
Max Act: 5.6123. Min Act: -0.1700
Data Index: 1864345 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7998. Min Range: -5.7998
Max Act: 5.6123. Min Act: -0.1700
Data Index: 4391910 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7998. Min Range: -5.7998
Max Act: 5.5810. Min Act: -0.1700
Data Index: 2896059 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7998. Min Range: -5.7998
Max Act: 5.6123. Min Act: -0.1700
Data Index: 8352100 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7998. Min Range: -5.7998
Max Act: 5.5810. Min Act: -0.1700
Data Index: 2005548 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7998. Min Range: -5.7998
Max Act: 5.5810. Min Act: -0.1700
Data Index: 6052649 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7998. Min Range: -5.7998
Max Act: 5.5810. Min Act: -0.1700
Data Index: 5817297 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7998. Min Range: -5.7998
Max Act: 5.5185. Min Act: -0.1700
Data Index: 5464741 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7998. Min Range: -5.7998
Max Act: 5.5185. Min Act: -0.1700
Data Index: 439773 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7998. Min Range: -5.7998
Max Act: 5.4873. Min Act: -0.1700
Data Index: 107915 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7998. Min Range: -5.7998
Max Act: 5.5185. Min Act: -0.1700
Data Index: 1922012 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #19