Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4884 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6825. Min Range: -5.6825
Max Act: 5.6825. Min Act: -0.1700
Data Index: 2392606 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6825. Min Range: -5.6825
Max Act: 5.6825. Min Act: -0.1700
Data Index: 457231 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6825. Min Range: -5.6825
Max Act: 5.6825. Min Act: -0.1700
Data Index: 2757378 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6825. Min Range: -5.6825
Max Act: 5.6825. Min Act: -0.1700
Data Index: 8168751 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6825. Min Range: -5.6825
Max Act: 5.6825. Min Act: -0.1700
Data Index: 7936552 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6825. Min Range: -5.6825
Max Act: 5.6513. Min Act: -0.1700
Data Index: 7344744 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6825. Min Range: -5.6825
Max Act: 5.6513. Min Act: -0.1700
Data Index: 4167205 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6825. Min Range: -5.6825
Max Act: 5.6200. Min Act: -0.1700
Data Index: 6589108 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6825. Min Range: -5.6825
Max Act: 5.5888. Min Act: -0.1700
Data Index: 2414548 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6825. Min Range: -5.6825
Max Act: 5.5888. Min Act: -0.1700
Data Index: 6166444 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6825. Min Range: -5.6825
Max Act: 5.5888. Min Act: -0.1700
Data Index: 3760700 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6825. Min Range: -5.6825
Max Act: 5.5575. Min Act: -0.1700
Data Index: 7427396 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6825. Min Range: -5.6825
Max Act: 5.5575. Min Act: -0.1700
Data Index: 4080706 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6825. Min Range: -5.6825
Max Act: 5.5575. Min Act: -0.1700
Data Index: 1422972 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6825. Min Range: -5.6825
Max Act: 5.5888. Min Act: -0.1700
Data Index: 3442313 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6825. Min Range: -5.6825
Max Act: 5.5575. Min Act: -0.1700
Data Index: 5597016 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6825. Min Range: -5.6825
Max Act: 5.5575. Min Act: -0.1700
Data Index: 3776804 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6825. Min Range: -5.6825
Max Act: 5.4950. Min Act: -0.1700
Data Index: 788381 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6825. Min Range: -5.6825
Max Act: 5.5263. Min Act: -0.1700
Data Index: 6912135 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6825. Min Range: -5.6825
Max Act: 5.4950. Min Act: -0.1700
Data Index: 6932770 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #19