Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3431 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3037. Min Range: -5.3037
Max Act: 5.3037. Min Act: -0.1700
Data Index: 3417703 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3037. Min Range: -5.3037
Max Act: 5.2724. Min Act: -0.1700
Data Index: 6551354 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3037. Min Range: -5.3037
Max Act: 5.1162. Min Act: -0.1700
Data Index: 1630351 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3037. Min Range: -5.3037
Max Act: 5.1162. Min Act: -0.1700
Data Index: 110387 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3037. Min Range: -5.3037
Max Act: 5.0849. Min Act: -0.1700
Data Index: 5347557 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3037. Min Range: -5.3037
Max Act: 5.0537. Min Act: -0.1700
Data Index: 2135436 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3037. Min Range: -5.3037
Max Act: 5.0537. Min Act: -0.1700
Data Index: 8338760 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3037. Min Range: -5.3037
Max Act: 5.0537. Min Act: -0.1700
Data Index: 4026368 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3037. Min Range: -5.3037
Max Act: 5.0537. Min Act: -0.1700
Data Index: 7584799 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3037. Min Range: -5.3037
Max Act: 5.0537. Min Act: -0.1700
Data Index: 6589087 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3037. Min Range: -5.3037
Max Act: 5.0849. Min Act: -0.1700
Data Index: 2427687 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3037. Min Range: -5.3037
Max Act: 5.0224. Min Act: -0.1700
Data Index: 1749434 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3037. Min Range: -5.3037
Max Act: 5.0537. Min Act: -0.1700
Data Index: 7796058 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3037. Min Range: -5.3037
Max Act: 4.9912. Min Act: -0.1700
Data Index: 8142505 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3037. Min Range: -5.3037
Max Act: 4.9912. Min Act: -0.1700
Data Index: 8579822 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3037. Min Range: -5.3037
Max Act: 5.0224. Min Act: -0.1700
Data Index: 2677911 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3037. Min Range: -5.3037
Max Act: 5.0224. Min Act: -0.1700
Data Index: 1090063 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3037. Min Range: -5.3037
Max Act: 4.9599. Min Act: -0.1700
Data Index: 416893 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3037. Min Range: -5.3037
Max Act: 4.9599. Min Act: -0.1700
Data Index: 995771 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3037. Min Range: -5.3037
Max Act: 4.9287. Min Act: -0.1700
Data Index: 4556647 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #19