Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2593 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8377. Min Range: -2.8377
Max Act: 2.8377. Min Act: -0.1697
Data Index: 5848526 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8377. Min Range: -2.8377
Max Act: 2.8377. Min Act: -0.1700
Data Index: 1430011 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8377. Min Range: -2.8377
Max Act: 2.8059. Min Act: -0.1700
Data Index: 4744291 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8377. Min Range: -2.8377
Max Act: 2.7740. Min Act: -0.1700
Data Index: 5164461 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8377. Min Range: -2.8377
Max Act: 2.7581. Min Act: -0.1700
Data Index: 6973502 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8377. Min Range: -2.8377
Max Act: 2.7581. Min Act: -0.1700
Data Index: 5644979 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8377. Min Range: -2.8377
Max Act: 2.7581. Min Act: -0.1700
Data Index: 2439918 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8377. Min Range: -2.8377
Max Act: 2.7421. Min Act: -0.1700
Data Index: 2392053 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8377. Min Range: -2.8377
Max Act: 2.7421. Min Act: -0.1700
Data Index: 4397987 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8377. Min Range: -2.8377
Max Act: 2.7421. Min Act: -0.1700
Data Index: 8561755 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8377. Min Range: -2.8377
Max Act: 2.7262. Min Act: -0.1700
Data Index: 4507586 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8377. Min Range: -2.8377
Max Act: 2.7262. Min Act: -0.1700
Data Index: 7813420 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8377. Min Range: -2.8377
Max Act: 2.7262. Min Act: -0.1700
Data Index: 3588467 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8377. Min Range: -2.8377
Max Act: 2.7262. Min Act: -0.1700
Data Index: 3046845 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8377. Min Range: -2.8377
Max Act: 2.7262. Min Act: -0.1700
Data Index: 451670 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8377. Min Range: -2.8377
Max Act: 2.7262. Min Act: -0.1700
Data Index: 4935882 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8377. Min Range: -2.8377
Max Act: 2.7262. Min Act: -0.1700
Data Index: 2934463 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8377. Min Range: -2.8377
Max Act: 2.7102. Min Act: -0.1700
Data Index: 3365496 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8377. Min Range: -2.8377
Max Act: 2.7102. Min Act: -0.1700
Data Index: 6565112 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8377. Min Range: -2.8377
Max Act: 2.7102. Min Act: -0.1700
Data Index: 6565704 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19