Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3052 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6357. Min Range: -6.6357
Max Act: 6.6357. Min Act: -0.1700
Data Index: 6150470 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6357. Min Range: -6.6357
Max Act: 6.6357. Min Act: -0.1700
Data Index: 1922815 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6357. Min Range: -6.6357
Max Act: 6.5732. Min Act: -0.1700
Data Index: 949576 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6357. Min Range: -6.6357
Max Act: 6.5419. Min Act: -0.1700
Data Index: 750557 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6357. Min Range: -6.6357
Max Act: 6.5419. Min Act: -0.1700
Data Index: 1911193 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6357. Min Range: -6.6357
Max Act: 6.4169. Min Act: -0.1700
Data Index: 42264 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6357. Min Range: -6.6357
Max Act: 6.3857. Min Act: -0.1700
Data Index: 986306 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6357. Min Range: -6.6357
Max Act: 6.2294. Min Act: -0.1700
Data Index: 5736287 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6357. Min Range: -6.6357
Max Act: 6.1982. Min Act: -0.1700
Data Index: 5736283 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6357. Min Range: -6.6357
Max Act: 6.1982. Min Act: -0.1700
Data Index: 3121765 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6357. Min Range: -6.6357
Max Act: 6.2294. Min Act: -0.1700
Data Index: 1888002 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6357. Min Range: -6.6357
Max Act: 6.1669. Min Act: -0.1700
Data Index: 6722350 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6357. Min Range: -6.6357
Max Act: 6.1982. Min Act: -0.1700
Data Index: 5083495 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6357. Min Range: -6.6357
Max Act: 6.1357. Min Act: -0.1700
Data Index: 545824 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6357. Min Range: -6.6357
Max Act: 6.1669. Min Act: -0.1700
Data Index: 6447993 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6357. Min Range: -6.6357
Max Act: 6.1044. Min Act: -0.1700
Data Index: 162114 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6357. Min Range: -6.6357
Max Act: 6.0732. Min Act: -0.1700
Data Index: 3179103 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6357. Min Range: -6.6357
Max Act: 6.0732. Min Act: -0.1700
Data Index: 146166 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6357. Min Range: -6.6357
Max Act: 6.1044. Min Act: -0.1700
Data Index: 4267836 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6357. Min Range: -6.6357
Max Act: 5.9794. Min Act: -0.1700
Data Index: 1743682 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #19