Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3678 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8092. Min Range: -8.8092
Max Act: 8.8092. Min Act: -0.1700
Data Index: 7172432 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8092. Min Range: -8.8092
Max Act: 8.7467. Min Act: -0.1700
Data Index: 6707470 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8092. Min Range: -8.8092
Max Act: 8.6217. Min Act: -0.1700
Data Index: 7856789 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8092. Min Range: -8.8092
Max Act: 8.4967. Min Act: -0.1700
Data Index: 6806310 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8092. Min Range: -8.8092
Max Act: 8.3717. Min Act: -0.1700
Data Index: 1542234 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8092. Min Range: -8.8092
Max Act: 8.3717. Min Act: -0.1700
Data Index: 7391594 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8092. Min Range: -8.8092
Max Act: 8.3092. Min Act: -0.1700
Data Index: 7867275 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8092. Min Range: -8.8092
Max Act: 8.2467. Min Act: -0.1700
Data Index: 647115 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8092. Min Range: -8.8092
Max Act: 8.1842. Min Act: -0.1700
Data Index: 1480894 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8092. Min Range: -8.8092
Max Act: 8.1842. Min Act: -0.1700
Data Index: 3126635 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8092. Min Range: -8.8092
Max Act: 8.1217. Min Act: -0.1700
Data Index: 7181656 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8092. Min Range: -8.8092
Max Act: 8.1217. Min Act: -0.1700
Data Index: 2022275 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8092. Min Range: -8.8092
Max Act: 8.1217. Min Act: -0.1700
Data Index: 7357514 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8092. Min Range: -8.8092
Max Act: 8.1217. Min Act: -0.1700
Data Index: 6100300 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8092. Min Range: -8.8092
Max Act: 8.0592. Min Act: -0.1700
Data Index: 4689991 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8092. Min Range: -8.8092
Max Act: 8.0592. Min Act: -0.1700
Data Index: 7201951 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8092. Min Range: -8.8092
Max Act: 8.0592. Min Act: -0.1700
Data Index: 6982560 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8092. Min Range: -8.8092
Max Act: 8.0592. Min Act: -0.1700
Data Index: 4299434 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8092. Min Range: -8.8092
Max Act: 7.9342. Min Act: -0.1700
Data Index: 5254796 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8092. Min Range: -8.8092
Max Act: 7.9967. Min Act: -0.1700
Data Index: 6944225 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #19