Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2480 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8042. Min Range: -7.8042
Max Act: 7.8042. Min Act: -0.1700
Data Index: 884143 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8042. Min Range: -7.8042
Max Act: 6.8979. Min Act: -0.1700
Data Index: 1096713 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8042. Min Range: -7.8042
Max Act: 6.7729. Min Act: -0.1700
Data Index: 4787320 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8042. Min Range: -7.8042
Max Act: 6.7104. Min Act: -0.1700
Data Index: 3132140 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8042. Min Range: -7.8042
Max Act: 6.5854. Min Act: -0.1700
Data Index: 3876941 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8042. Min Range: -7.8042
Max Act: 6.5854. Min Act: -0.1700
Data Index: 7512257 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8042. Min Range: -7.8042
Max Act: 6.5854. Min Act: -0.1700
Data Index: 6910363 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8042. Min Range: -7.8042
Max Act: 6.5854. Min Act: -0.1700
Data Index: 1611402 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8042. Min Range: -7.8042
Max Act: 6.5229. Min Act: -0.1700
Data Index: 2979038 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8042. Min Range: -7.8042
Max Act: 6.4917. Min Act: -0.1700
Data Index: 54889 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8042. Min Range: -7.8042
Max Act: 6.4917. Min Act: -0.1700
Data Index: 122769 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8042. Min Range: -7.8042
Max Act: 6.4917. Min Act: -0.1700
Data Index: 7790266 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8042. Min Range: -7.8042
Max Act: 6.4604. Min Act: -0.1700
Data Index: 3620008 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8042. Min Range: -7.8042
Max Act: 6.4292. Min Act: -0.1700
Data Index: 7560098 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8042. Min Range: -7.8042
Max Act: 6.4292. Min Act: -0.1700
Data Index: 972355 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8042. Min Range: -7.8042
Max Act: 6.3667. Min Act: -0.1700
Data Index: 4971800 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8042. Min Range: -7.8042
Max Act: 6.3667. Min Act: -0.1700
Data Index: 4758708 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8042. Min Range: -7.8042
Max Act: 6.4292. Min Act: -0.1700
Data Index: 2249674 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8042. Min Range: -7.8042
Max Act: 6.3979. Min Act: -0.1700
Data Index: 4913946 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8042. Min Range: -7.8042
Max Act: 6.3979. Min Act: -0.1700
Data Index: 4104952 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #19