Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3721 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4278. Min Range: -6.4278
Max Act: 6.4278. Min Act: -0.1700
Data Index: 4862542 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4278. Min Range: -6.4278
Max Act: 6.1778. Min Act: -0.1700
Data Index: 2199254 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4278. Min Range: -6.4278
Max Act: 6.1153. Min Act: -0.1700
Data Index: 5036041 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4278. Min Range: -6.4278
Max Act: 6.0841. Min Act: -0.1700
Data Index: 8557422 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4278. Min Range: -6.4278
Max Act: 6.0528. Min Act: -0.1700
Data Index: 4151709 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4278. Min Range: -6.4278
Max Act: 5.9903. Min Act: -0.1700
Data Index: 2988728 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4278. Min Range: -6.4278
Max Act: 5.8966. Min Act: -0.1700
Data Index: 3629628 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4278. Min Range: -6.4278
Max Act: 5.8653. Min Act: -0.1700
Data Index: 8168503 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4278. Min Range: -6.4278
Max Act: 5.8653. Min Act: -0.1700
Data Index: 3202967 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4278. Min Range: -6.4278
Max Act: 5.8653. Min Act: -0.1700
Data Index: 7648492 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4278. Min Range: -6.4278
Max Act: 5.8653. Min Act: -0.1700
Data Index: 3520999 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4278. Min Range: -6.4278
Max Act: 5.8653. Min Act: -0.1700
Data Index: 6479711 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4278. Min Range: -6.4278
Max Act: 5.8653. Min Act: -0.1700
Data Index: 7516068 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4278. Min Range: -6.4278
Max Act: 5.8341. Min Act: -0.1700
Data Index: 2890916 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4278. Min Range: -6.4278
Max Act: 5.8028. Min Act: -0.1700
Data Index: 6488746 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4278. Min Range: -6.4278
Max Act: 5.8653. Min Act: -0.1700
Data Index: 2021541 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4278. Min Range: -6.4278
Max Act: 5.8341. Min Act: -0.1700
Data Index: 6911928 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4278. Min Range: -6.4278
Max Act: 5.8028. Min Act: -0.1700
Data Index: 3840377 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4278. Min Range: -6.4278
Max Act: 5.8341. Min Act: -0.1700
Data Index: 6843524 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4278. Min Range: -6.4278
Max Act: 5.8653. Min Act: -0.1700
Data Index: 8215124 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #19