Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4164 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6153. Min Range: -6.6153
Max Act: 6.6153. Min Act: -0.1700
Data Index: 391194 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6153. Min Range: -6.6153
Max Act: 6.1153. Min Act: -0.1700
Data Index: 964471 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6153. Min Range: -6.6153
Max Act: 6.0528. Min Act: -0.1700
Data Index: 8430681 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6153. Min Range: -6.6153
Max Act: 6.0840. Min Act: -0.1700
Data Index: 2583801 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6153. Min Range: -6.6153
Max Act: 6.0528. Min Act: -0.1700
Data Index: 5991764 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6153. Min Range: -6.6153
Max Act: 6.0215. Min Act: -0.1700
Data Index: 8632710 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6153. Min Range: -6.6153
Max Act: 5.9590. Min Act: -0.1700
Data Index: 2192608 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6153. Min Range: -6.6153
Max Act: 5.8965. Min Act: -0.1700
Data Index: 8400410 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6153. Min Range: -6.6153
Max Act: 5.9278. Min Act: -0.1700
Data Index: 7040495 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6153. Min Range: -6.6153
Max Act: 5.8965. Min Act: -0.1700
Data Index: 7377650 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6153. Min Range: -6.6153
Max Act: 5.8340. Min Act: -0.1700
Data Index: 5865316 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6153. Min Range: -6.6153
Max Act: 5.8653. Min Act: -0.1700
Data Index: 4735563 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6153. Min Range: -6.6153
Max Act: 5.8653. Min Act: -0.1700
Data Index: 3344884 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6153. Min Range: -6.6153
Max Act: 5.8340. Min Act: -0.1700
Data Index: 6986396 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6153. Min Range: -6.6153
Max Act: 5.8340. Min Act: -0.1700
Data Index: 4209482 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6153. Min Range: -6.6153
Max Act: 5.8028. Min Act: -0.1700
Data Index: 3591807 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6153. Min Range: -6.6153
Max Act: 5.8028. Min Act: -0.1700
Data Index: 7319707 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6153. Min Range: -6.6153
Max Act: 5.7715. Min Act: -0.1700
Data Index: 7975864 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6153. Min Range: -6.6153
Max Act: 5.7403. Min Act: -0.1700
Data Index: 3448627 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6153. Min Range: -6.6153
Max Act: 5.8028. Min Act: -0.1700
Data Index: 7781681 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #19