Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2729 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5320. Min Range: -8.5320
Max Act: 8.5320. Min Act: -0.1700
Data Index: 8330324 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5320. Min Range: -8.5320
Max Act: 8.4695. Min Act: -0.1700
Data Index: 6736774 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5320. Min Range: -8.5320
Max Act: 8.3445. Min Act: -0.1700
Data Index: 1694424 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5320. Min Range: -8.5320
Max Act: 8.2820. Min Act: -0.1700
Data Index: 5159177 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5320. Min Range: -8.5320
Max Act: 8.1570. Min Act: -0.1700
Data Index: 2606389 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5320. Min Range: -8.5320
Max Act: 8.0320. Min Act: -0.1700
Data Index: 2838784 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5320. Min Range: -8.5320
Max Act: 7.9695. Min Act: -0.1700
Data Index: 2918913 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5320. Min Range: -8.5320
Max Act: 7.9695. Min Act: -0.1700
Data Index: 6897878 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5320. Min Range: -8.5320
Max Act: 7.9070. Min Act: -0.1700
Data Index: 985750 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5320. Min Range: -8.5320
Max Act: 7.8445. Min Act: -0.1700
Data Index: 2270361 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5320. Min Range: -8.5320
Max Act: 7.9070. Min Act: -0.1700
Data Index: 3870063 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5320. Min Range: -8.5320
Max Act: 7.9070. Min Act: -0.1700
Data Index: 2403948 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5320. Min Range: -8.5320
Max Act: 7.9070. Min Act: -0.1700
Data Index: 4838065 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5320. Min Range: -8.5320
Max Act: 7.8445. Min Act: -0.1700
Data Index: 1370334 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5320. Min Range: -8.5320
Max Act: 7.7820. Min Act: -0.1700
Data Index: 7824818 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5320. Min Range: -8.5320
Max Act: 7.7820. Min Act: -0.1700
Data Index: 3857843 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5320. Min Range: -8.5320
Max Act: 7.7820. Min Act: -0.1700
Data Index: 6222134 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5320. Min Range: -8.5320
Max Act: 7.7820. Min Act: -0.1700
Data Index: 5535242 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5320. Min Range: -8.5320
Max Act: 7.7820. Min Act: -0.1700
Data Index: 4170695 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5320. Min Range: -8.5320
Max Act: 7.7820. Min Act: -0.1700
Data Index: 7496484 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #19