Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3243 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5827. Min Range: -6.5827
Max Act: 6.5827. Min Act: -0.1700
Data Index: 5466138 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5827. Min Range: -6.5827
Max Act: 6.5515. Min Act: -0.1700
Data Index: 7580954 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5827. Min Range: -6.5827
Max Act: 6.5515. Min Act: -0.1700
Data Index: 3301759 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5827. Min Range: -6.5827
Max Act: 6.4890. Min Act: -0.1700
Data Index: 8148808 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5827. Min Range: -6.5827
Max Act: 6.4265. Min Act: -0.1700
Data Index: 3986100 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5827. Min Range: -6.5827
Max Act: 6.4265. Min Act: -0.1700
Data Index: 1868526 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5827. Min Range: -6.5827
Max Act: 6.4265. Min Act: -0.1700
Data Index: 4708175 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5827. Min Range: -6.5827
Max Act: 6.4265. Min Act: -0.1700
Data Index: 2024765 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5827. Min Range: -6.5827
Max Act: 6.4265. Min Act: -0.1700
Data Index: 3434226 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5827. Min Range: -6.5827
Max Act: 6.3640. Min Act: -0.1700
Data Index: 7355842 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5827. Min Range: -6.5827
Max Act: 6.3640. Min Act: -0.1700
Data Index: 7176985 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5827. Min Range: -6.5827
Max Act: 6.3327. Min Act: -0.1700
Data Index: 4560954 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5827. Min Range: -6.5827
Max Act: 6.3327. Min Act: -0.1700
Data Index: 2867715 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5827. Min Range: -6.5827
Max Act: 6.3327. Min Act: -0.1700
Data Index: 6006187 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5827. Min Range: -6.5827
Max Act: 6.3015. Min Act: -0.1700
Data Index: 6544934 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5827. Min Range: -6.5827
Max Act: 6.3015. Min Act: -0.1700
Data Index: 4144403 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5827. Min Range: -6.5827
Max Act: 6.2390. Min Act: -0.1700
Data Index: 656601 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5827. Min Range: -6.5827
Max Act: 6.2702. Min Act: -0.1700
Data Index: 4640509 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5827. Min Range: -6.5827
Max Act: 6.2702. Min Act: -0.1700
Data Index: 1624907 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5827. Min Range: -6.5827
Max Act: 6.2702. Min Act: -0.1700
Data Index: 6754560 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #19