Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3420 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0774. Min Range: -7.0774
Max Act: 7.0774. Min Act: -0.1700
Data Index: 6223416 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0774. Min Range: -7.0774
Max Act: 6.8587. Min Act: -0.1700
Data Index: 722014 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0774. Min Range: -7.0774
Max Act: 6.7962. Min Act: -0.1700
Data Index: 4061557 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0774. Min Range: -7.0774
Max Act: 6.7024. Min Act: -0.1700
Data Index: 2815893 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0774. Min Range: -7.0774
Max Act: 6.7024. Min Act: -0.1700
Data Index: 7674570 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0774. Min Range: -7.0774
Max Act: 6.7024. Min Act: -0.1700
Data Index: 1091897 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0774. Min Range: -7.0774
Max Act: 6.6399. Min Act: -0.1700
Data Index: 2123112 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0774. Min Range: -7.0774
Max Act: 6.6399. Min Act: -0.1700
Data Index: 6583745 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0774. Min Range: -7.0774
Max Act: 6.6087. Min Act: -0.1700
Data Index: 650415 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0774. Min Range: -7.0774
Max Act: 6.6087. Min Act: -0.1700
Data Index: 23794 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0774. Min Range: -7.0774
Max Act: 6.6087. Min Act: -0.1700
Data Index: 5427706 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0774. Min Range: -7.0774
Max Act: 6.5774. Min Act: -0.1700
Data Index: 2223333 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0774. Min Range: -7.0774
Max Act: 6.5774. Min Act: -0.1700
Data Index: 7506859 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0774. Min Range: -7.0774
Max Act: 6.5774. Min Act: -0.1700
Data Index: 4679115 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0774. Min Range: -7.0774
Max Act: 6.5149. Min Act: -0.1700
Data Index: 3087042 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0774. Min Range: -7.0774
Max Act: 6.5462. Min Act: -0.1700
Data Index: 7427994 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0774. Min Range: -7.0774
Max Act: 6.5462. Min Act: -0.1700
Data Index: 3889531 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0774. Min Range: -7.0774
Max Act: 6.5462. Min Act: -0.1700
Data Index: 8458816 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0774. Min Range: -7.0774
Max Act: 6.5149. Min Act: -0.1700
Data Index: 622705 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0774. Min Range: -7.0774
Max Act: 6.5149. Min Act: -0.1700
Data Index: 4809976 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #19