Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1815 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6826. Min Range: -3.6826
Max Act: 3.6826. Min Act: -0.1700
Data Index: 3817829 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6826. Min Range: -3.6826
Max Act: 3.3851. Min Act: -0.1700
Data Index: 4151453 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6826. Min Range: -3.6826
Max Act: 3.3694. Min Act: -0.1700
Data Index: 1665606 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6826. Min Range: -3.6826
Max Act: 3.3537. Min Act: -0.1700
Data Index: 3106672 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6826. Min Range: -3.6826
Max Act: 3.3223. Min Act: -0.1700
Data Index: 1620634 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6826. Min Range: -3.6826
Max Act: 3.3380. Min Act: -0.1700
Data Index: 7258148 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6826. Min Range: -3.6826
Max Act: 3.3066. Min Act: -0.1700
Data Index: 6467392 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6826. Min Range: -3.6826
Max Act: 3.3066. Min Act: -0.1700
Data Index: 2049750 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6826. Min Range: -3.6826
Max Act: 3.2595. Min Act: -0.1700
Data Index: 1951559 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6826. Min Range: -3.6826
Max Act: 3.2752. Min Act: -0.1700
Data Index: 6216839 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6826. Min Range: -3.6826
Max Act: 3.2438. Min Act: -0.1700
Data Index: 4381390 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6826. Min Range: -3.6826
Max Act: 3.2595. Min Act: -0.1700
Data Index: 221745 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6826. Min Range: -3.6826
Max Act: 3.2438. Min Act: -0.1700
Data Index: 4332934 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6826. Min Range: -3.6826
Max Act: 3.2438. Min Act: -0.1700
Data Index: 7066464 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6826. Min Range: -3.6826
Max Act: 3.2438. Min Act: -0.1700
Data Index: 6771005 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6826. Min Range: -3.6826
Max Act: 3.2281. Min Act: -0.1700
Data Index: 8192207 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6826. Min Range: -3.6826
Max Act: 3.2281. Min Act: -0.1700
Data Index: 6175418 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6826. Min Range: -3.6826
Max Act: 3.2281. Min Act: -0.1700
Data Index: 5612802 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6826. Min Range: -3.6826
Max Act: 3.2281. Min Act: -0.1700
Data Index: 2687628 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6826. Min Range: -3.6826
Max Act: 3.2124. Min Act: -0.1700
Data Index: 2588549 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #19