Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2739 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9036. Min Range: -5.9036
Max Act: 5.9036. Min Act: -0.1700
Data Index: 825894 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9036. Min Range: -5.9036
Max Act: 5.7786. Min Act: -0.1700
Data Index: 6088948 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9036. Min Range: -5.9036
Max Act: 5.5286. Min Act: -0.1700
Data Index: 7322483 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9036. Min Range: -5.9036
Max Act: 5.4348. Min Act: -0.1700
Data Index: 6809690 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9036. Min Range: -5.9036
Max Act: 5.3411. Min Act: -0.1700
Data Index: 1872501 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9036. Min Range: -5.9036
Max Act: 5.3098. Min Act: -0.1700
Data Index: 5814775 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9036. Min Range: -5.9036
Max Act: 5.2161. Min Act: -0.1700
Data Index: 3905860 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9036. Min Range: -5.9036
Max Act: 5.1848. Min Act: -0.1700
Data Index: 4280464 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9036. Min Range: -5.9036
Max Act: 5.1536. Min Act: -0.1700
Data Index: 8050201 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9036. Min Range: -5.9036
Max Act: 5.1223. Min Act: -0.1700
Data Index: 3396512 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9036. Min Range: -5.9036
Max Act: 5.1223. Min Act: -0.1700
Data Index: 225082 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9036. Min Range: -5.9036
Max Act: 5.0911. Min Act: -0.1700
Data Index: 1212891 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9036. Min Range: -5.9036
Max Act: 5.1223. Min Act: -0.1700
Data Index: 3950991 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9036. Min Range: -5.9036
Max Act: 5.1223. Min Act: -0.1700
Data Index: 1571187 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9036. Min Range: -5.9036
Max Act: 5.1223. Min Act: -0.1700
Data Index: 2235676 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9036. Min Range: -5.9036
Max Act: 5.0911. Min Act: -0.1700
Data Index: 3014403 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9036. Min Range: -5.9036
Max Act: 5.0911. Min Act: -0.1700
Data Index: 6303879 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9036. Min Range: -5.9036
Max Act: 5.0911. Min Act: -0.1700
Data Index: 8565028 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9036. Min Range: -5.9036
Max Act: 5.0598. Min Act: -0.1700
Data Index: 756885 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9036. Min Range: -5.9036
Max Act: 5.0598. Min Act: -0.1700
Data Index: 1929859 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #19