Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3301 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2212. Min Range: -5.2212
Max Act: 5.2212. Min Act: -0.1700
Data Index: 6095606 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2212. Min Range: -5.2212
Max Act: 4.9712. Min Act: -0.1700
Data Index: 8492195 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2212. Min Range: -5.2212
Max Act: 4.9712. Min Act: -0.1700
Data Index: 1368252 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2212. Min Range: -5.2212
Max Act: 4.9400. Min Act: -0.1700
Data Index: 3906139 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2212. Min Range: -5.2212
Max Act: 4.9087. Min Act: -0.1700
Data Index: 5191111 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2212. Min Range: -5.2212
Max Act: 4.9400. Min Act: -0.1700
Data Index: 5910645 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2212. Min Range: -5.2212
Max Act: 4.9400. Min Act: -0.1700
Data Index: 4835707 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2212. Min Range: -5.2212
Max Act: 4.9087. Min Act: -0.1700
Data Index: 6592708 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2212. Min Range: -5.2212
Max Act: 4.9087. Min Act: -0.1700
Data Index: 5517591 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2212. Min Range: -5.2212
Max Act: 4.9087. Min Act: -0.1700
Data Index: 8204441 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2212. Min Range: -5.2212
Max Act: 4.8775. Min Act: -0.1700
Data Index: 210704 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2212. Min Range: -5.2212
Max Act: 4.8775. Min Act: -0.1700
Data Index: 1031270 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2212. Min Range: -5.2212
Max Act: 4.8462. Min Act: -0.1700
Data Index: 2888693 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2212. Min Range: -5.2212
Max Act: 4.8462. Min Act: -0.1700
Data Index: 4837514 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2212. Min Range: -5.2212
Max Act: 4.8462. Min Act: -0.1700
Data Index: 8571655 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2212. Min Range: -5.2212
Max Act: 4.8462. Min Act: -0.1700
Data Index: 2057113 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2212. Min Range: -5.2212
Max Act: 4.8462. Min Act: -0.1700
Data Index: 5621937 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2212. Min Range: -5.2212
Max Act: 4.8462. Min Act: -0.1700
Data Index: 7607444 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2212. Min Range: -5.2212
Max Act: 4.8462. Min Act: -0.1700
Data Index: 7513652 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2212. Min Range: -5.2212
Max Act: 4.8462. Min Act: -0.1700
Data Index: 1909225 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #19