Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5740 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7334. Min Range: -2.7334
Max Act: 2.7334. Min Act: -0.1700
Data Index: 2039736 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7334. Min Range: -2.7334
Max Act: 2.6854. Min Act: -0.1700
Data Index: 6621707 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7334. Min Range: -2.7334
Max Act: 2.6854. Min Act: -0.1700
Data Index: 8150444 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7334. Min Range: -2.7334
Max Act: 2.6534. Min Act: -0.1700
Data Index: 780109 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7334. Min Range: -2.7334
Max Act: 2.6534. Min Act: -0.1700
Data Index: 3097348 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7334. Min Range: -2.7334
Max Act: 2.6373. Min Act: -0.1700
Data Index: 6147849 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7334. Min Range: -2.7334
Max Act: 2.6052. Min Act: -0.1700
Data Index: 5891557 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7334. Min Range: -2.7334
Max Act: 2.5891. Min Act: -0.1700
Data Index: 6265134 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7334. Min Range: -2.7334
Max Act: 2.6212. Min Act: -0.1700
Data Index: 8738448 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7334. Min Range: -2.7334
Max Act: 2.6052. Min Act: -0.1700
Data Index: 6170677 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7334. Min Range: -2.7334
Max Act: 2.5891. Min Act: -0.1700
Data Index: 932507 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7334. Min Range: -2.7334
Max Act: 2.5891. Min Act: -0.1700
Data Index: 3467317 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7334. Min Range: -2.7334
Max Act: 2.5891. Min Act: -0.1700
Data Index: 8403416 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7334. Min Range: -2.7334
Max Act: 2.6052. Min Act: -0.1700
Data Index: 7344738 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7334. Min Range: -2.7334
Max Act: 2.5729. Min Act: -0.1700
Data Index: 4312346 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7334. Min Range: -2.7334
Max Act: 2.5729. Min Act: -0.1700
Data Index: 681570 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7334. Min Range: -2.7334
Max Act: 2.5729. Min Act: -0.1700
Data Index: 7564987 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7334. Min Range: -2.7334
Max Act: 2.5729. Min Act: -0.1700
Data Index: 1799455 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7334. Min Range: -2.7334
Max Act: 2.5729. Min Act: -0.1700
Data Index: 6268926 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7334. Min Range: -2.7334
Max Act: 2.5891. Min Act: -0.1700
Data Index: 5559358 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #19