Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2929 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2202. Min Range: -7.2202
Max Act: 7.2202. Min Act: -0.1700
Data Index: 172630 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2202. Min Range: -7.2202
Max Act: 7.1890. Min Act: -0.1700
Data Index: 4330517 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2202. Min Range: -7.2202
Max Act: 7.0952. Min Act: -0.1700
Data Index: 6306287 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2202. Min Range: -7.2202
Max Act: 7.0327. Min Act: -0.1700
Data Index: 4232730 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2202. Min Range: -7.2202
Max Act: 7.0015. Min Act: -0.1700
Data Index: 6967363 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2202. Min Range: -7.2202
Max Act: 7.0015. Min Act: -0.1700
Data Index: 2807827 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2202. Min Range: -7.2202
Max Act: 7.0015. Min Act: -0.1700
Data Index: 750945 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2202. Min Range: -7.2202
Max Act: 6.9702. Min Act: -0.1700
Data Index: 2869717 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2202. Min Range: -7.2202
Max Act: 6.9702. Min Act: -0.1700
Data Index: 6163027 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2202. Min Range: -7.2202
Max Act: 6.9077. Min Act: -0.1700
Data Index: 5870275 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2202. Min Range: -7.2202
Max Act: 6.9077. Min Act: -0.1700
Data Index: 4428382 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2202. Min Range: -7.2202
Max Act: 6.8765. Min Act: -0.1700
Data Index: 8452873 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2202. Min Range: -7.2202
Max Act: 6.8452. Min Act: -0.1700
Data Index: 834195 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2202. Min Range: -7.2202
Max Act: 6.8765. Min Act: -0.1700
Data Index: 4875654 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2202. Min Range: -7.2202
Max Act: 6.8140. Min Act: -0.1700
Data Index: 867923 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2202. Min Range: -7.2202
Max Act: 6.8452. Min Act: -0.1700
Data Index: 6356087 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2202. Min Range: -7.2202
Max Act: 6.8140. Min Act: -0.1700
Data Index: 2945359 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2202. Min Range: -7.2202
Max Act: 6.8452. Min Act: -0.1700
Data Index: 2260043 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2202. Min Range: -7.2202
Max Act: 6.8140. Min Act: -0.1700
Data Index: 4218649 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2202. Min Range: -7.2202
Max Act: 6.7827. Min Act: -0.1700
Data Index: 236979 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #19