Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4837 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9314. Min Range: -6.9314
Max Act: 6.9314. Min Act: -0.1700
Data Index: 818140 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9314. Min Range: -6.9314
Max Act: 6.8689. Min Act: -0.1700
Data Index: 5669517 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9314. Min Range: -6.9314
Max Act: 6.8064. Min Act: -0.1700
Data Index: 2571040 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9314. Min Range: -6.9314
Max Act: 6.7439. Min Act: -0.1700
Data Index: 4228197 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9314. Min Range: -6.9314
Max Act: 6.7126. Min Act: -0.1700
Data Index: 7099005 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9314. Min Range: -6.9314
Max Act: 6.7126. Min Act: -0.1700
Data Index: 1027630 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9314. Min Range: -6.9314
Max Act: 6.6814. Min Act: -0.1700
Data Index: 6858874 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9314. Min Range: -6.9314
Max Act: 6.6501. Min Act: -0.1700
Data Index: 7009210 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9314. Min Range: -6.9314
Max Act: 6.6501. Min Act: -0.1700
Data Index: 2403280 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9314. Min Range: -6.9314
Max Act: 6.6189. Min Act: -0.1700
Data Index: 3420204 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9314. Min Range: -6.9314
Max Act: 6.6189. Min Act: -0.1700
Data Index: 3353794 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9314. Min Range: -6.9314
Max Act: 6.5876. Min Act: -0.1700
Data Index: 2921646 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9314. Min Range: -6.9314
Max Act: 6.5251. Min Act: -0.1700
Data Index: 7707330 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9314. Min Range: -6.9314
Max Act: 6.5564. Min Act: -0.1700
Data Index: 2976162 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9314. Min Range: -6.9314
Max Act: 6.5251. Min Act: -0.1700
Data Index: 6018927 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9314. Min Range: -6.9314
Max Act: 6.5251. Min Act: -0.1700
Data Index: 2329569 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9314. Min Range: -6.9314
Max Act: 6.4939. Min Act: -0.1700
Data Index: 6055625 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9314. Min Range: -6.9314
Max Act: 6.4939. Min Act: -0.1700
Data Index: 7510699 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9314. Min Range: -6.9314
Max Act: 6.5251. Min Act: -0.1700
Data Index: 4031949 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9314. Min Range: -6.9314
Max Act: 6.4626. Min Act: -0.1700
Data Index: 2821483 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #19