Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 652 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0317. Min Range: -6.0317
Max Act: 6.0317. Min Act: -0.1700
Data Index: 348295 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0317. Min Range: -6.0317
Max Act: 5.8130. Min Act: -0.1700
Data Index: 2742609 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0317. Min Range: -6.0317
Max Act: 5.8130. Min Act: -0.1700
Data Index: 3537640 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0317. Min Range: -6.0317
Max Act: 5.7192. Min Act: -0.1700
Data Index: 3078550 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0317. Min Range: -6.0317
Max Act: 5.6567. Min Act: -0.1700
Data Index: 7943827 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0317. Min Range: -6.0317
Max Act: 5.6567. Min Act: -0.1700
Data Index: 1504522 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0317. Min Range: -6.0317
Max Act: 5.6567. Min Act: -0.1700
Data Index: 1843606 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0317. Min Range: -6.0317
Max Act: 5.6255. Min Act: -0.1700
Data Index: 8457681 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0317. Min Range: -6.0317
Max Act: 5.5942. Min Act: -0.1700
Data Index: 6484940 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0317. Min Range: -6.0317
Max Act: 5.5942. Min Act: -0.1700
Data Index: 4408213 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0317. Min Range: -6.0317
Max Act: 5.5942. Min Act: -0.1700
Data Index: 141542 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0317. Min Range: -6.0317
Max Act: 5.5942. Min Act: -0.1700
Data Index: 3668437 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0317. Min Range: -6.0317
Max Act: 5.5942. Min Act: -0.1700
Data Index: 8751795 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0317. Min Range: -6.0317
Max Act: 5.5942. Min Act: -0.1700
Data Index: 6757961 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0317. Min Range: -6.0317
Max Act: 5.5630. Min Act: -0.1700
Data Index: 8172139 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0317. Min Range: -6.0317
Max Act: 5.5630. Min Act: -0.1700
Data Index: 183470 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0317. Min Range: -6.0317
Max Act: 5.5005. Min Act: -0.1700
Data Index: 2885300 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0317. Min Range: -6.0317
Max Act: 5.5005. Min Act: -0.1700
Data Index: 5594396 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0317. Min Range: -6.0317
Max Act: 5.5317. Min Act: -0.1700
Data Index: 6394752 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0317. Min Range: -6.0317
Max Act: 5.5317. Min Act: -0.1700
Data Index: 1338341 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #19