Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3507 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1561. Min Range: -3.1561
Max Act: 3.1561. Min Act: -0.1700
Data Index: 2571459 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1561. Min Range: -3.1561
Max Act: 3.0931. Min Act: -0.1700
Data Index: 6877953 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1561. Min Range: -3.1561
Max Act: 3.0931. Min Act: -0.1700
Data Index: 7557952 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1561. Min Range: -3.1561
Max Act: 3.0773. Min Act: -0.1700
Data Index: 2504499 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1561. Min Range: -3.1561
Max Act: 3.0773. Min Act: -0.1700
Data Index: 1654029 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1561. Min Range: -3.1561
Max Act: 3.0615. Min Act: -0.1700
Data Index: 1718217 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1561. Min Range: -3.1561
Max Act: 3.0615. Min Act: -0.1700
Data Index: 3221580 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1561. Min Range: -3.1561
Max Act: 3.0615. Min Act: -0.1700
Data Index: 8648314 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1561. Min Range: -3.1561
Max Act: 3.0458. Min Act: -0.1700
Data Index: 4055727 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1561. Min Range: -3.1561
Max Act: 3.0458. Min Act: -0.1700
Data Index: 7780882 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1561. Min Range: -3.1561
Max Act: 3.0458. Min Act: -0.1700
Data Index: 746392 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1561. Min Range: -3.1561
Max Act: 3.0615. Min Act: -0.1700
Data Index: 4203903 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1561. Min Range: -3.1561
Max Act: 3.0458. Min Act: -0.1700
Data Index: 3710724 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1561. Min Range: -3.1561
Max Act: 3.0615. Min Act: -0.1700
Data Index: 7174409 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1561. Min Range: -3.1561
Max Act: 3.0458. Min Act: -0.1700
Data Index: 8480780 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1561. Min Range: -3.1561
Max Act: 3.0458. Min Act: -0.1700
Data Index: 624877 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1561. Min Range: -3.1561
Max Act: 3.0458. Min Act: -0.1700
Data Index: 6787169 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1561. Min Range: -3.1561
Max Act: 3.0300. Min Act: -0.1700
Data Index: 7807438 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1561. Min Range: -3.1561
Max Act: 3.0300. Min Act: -0.1700
Data Index: 642150 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1561. Min Range: -3.1561
Max Act: 3.0300. Min Act: -0.1700
Data Index: 7761975 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19