Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4698 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9621. Min Range: -8.9621
Max Act: 8.9621. Min Act: -0.1700
Data Index: 525747 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9621. Min Range: -8.9621
Max Act: 8.7746. Min Act: -0.1700
Data Index: 5087372 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9621. Min Range: -8.9621
Max Act: 8.7121. Min Act: -0.1700
Data Index: 2058647 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9621. Min Range: -8.9621
Max Act: 8.4621. Min Act: -0.1700
Data Index: 3484968 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9621. Min Range: -8.9621
Max Act: 8.3683. Min Act: -0.1700
Data Index: 6539860 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9621. Min Range: -8.9621
Max Act: 8.3058. Min Act: -0.1700
Data Index: 6512605 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9621. Min Range: -8.9621
Max Act: 8.3371. Min Act: -0.1700
Data Index: 706201 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9621. Min Range: -8.9621
Max Act: 8.2746. Min Act: -0.1700
Data Index: 6350546 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9621. Min Range: -8.9621
Max Act: 8.2746. Min Act: -0.1700
Data Index: 6011004 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9621. Min Range: -8.9621
Max Act: 8.1496. Min Act: -0.1700
Data Index: 872682 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9621. Min Range: -8.9621
Max Act: 8.1496. Min Act: -0.1700
Data Index: 3291788 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9621. Min Range: -8.9621
Max Act: 8.1183. Min Act: -0.1700
Data Index: 4252462 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9621. Min Range: -8.9621
Max Act: 8.0871. Min Act: -0.1700
Data Index: 2936082 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9621. Min Range: -8.9621
Max Act: 8.0871. Min Act: -0.1700
Data Index: 8277544 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9621. Min Range: -8.9621
Max Act: 8.0871. Min Act: -0.1700
Data Index: 3772553 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9621. Min Range: -8.9621
Max Act: 8.0558. Min Act: -0.1700
Data Index: 3647140 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9621. Min Range: -8.9621
Max Act: 8.0558. Min Act: -0.1700
Data Index: 4251888 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9621. Min Range: -8.9621
Max Act: 8.0246. Min Act: -0.1700
Data Index: 3715888 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9621. Min Range: -8.9621
Max Act: 7.9933. Min Act: -0.1700
Data Index: 7804326 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9621. Min Range: -8.9621
Max Act: 8.0246. Min Act: -0.1700
Data Index: 4024833 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #19