Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2757 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8294. Min Range: -6.8294
Max Act: 6.8294. Min Act: -0.1700
Data Index: 1800340 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8294. Min Range: -6.8294
Max Act: 6.6107. Min Act: -0.1700
Data Index: 2871465 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8294. Min Range: -6.8294
Max Act: 6.5482. Min Act: -0.1700
Data Index: 4662711 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8294. Min Range: -6.8294
Max Act: 6.3607. Min Act: -0.1700
Data Index: 4034936 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8294. Min Range: -6.8294
Max Act: 6.3294. Min Act: -0.1700
Data Index: 7790159 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8294. Min Range: -6.8294
Max Act: 6.2982. Min Act: -0.1700
Data Index: 4980891 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8294. Min Range: -6.8294
Max Act: 6.3294. Min Act: -0.1700
Data Index: 232874 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8294. Min Range: -6.8294
Max Act: 6.2982. Min Act: -0.1700
Data Index: 5241500 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8294. Min Range: -6.8294
Max Act: 6.2669. Min Act: -0.1700
Data Index: 7373026 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8294. Min Range: -6.8294
Max Act: 6.2357. Min Act: -0.1700
Data Index: 5775375 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8294. Min Range: -6.8294
Max Act: 6.2357. Min Act: -0.1700
Data Index: 5967624 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8294. Min Range: -6.8294
Max Act: 6.1419. Min Act: -0.1700
Data Index: 5324926 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8294. Min Range: -6.8294
Max Act: 6.1419. Min Act: -0.1700
Data Index: 230482 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8294. Min Range: -6.8294
Max Act: 6.1107. Min Act: -0.1700
Data Index: 6337147 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8294. Min Range: -6.8294
Max Act: 6.1107. Min Act: -0.1700
Data Index: 1814778 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8294. Min Range: -6.8294
Max Act: 6.1107. Min Act: -0.1700
Data Index: 7434744 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8294. Min Range: -6.8294
Max Act: 6.0794. Min Act: -0.1700
Data Index: 6997868 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8294. Min Range: -6.8294
Max Act: 6.0169. Min Act: -0.1700
Data Index: 102497 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8294. Min Range: -6.8294
Max Act: 6.0169. Min Act: -0.1700
Data Index: 5277566 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8294. Min Range: -6.8294
Max Act: 5.9857. Min Act: -0.1700
Data Index: 3641752 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #19