Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3364 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.3572. Min Range: -2.3572
Max Act: 2.3572. Min Act: -0.1698
Data Index: 4465300 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3572. Min Range: -2.3572
Max Act: 2.3079. Min Act: -0.1700
Data Index: 4653130 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3572. Min Range: -2.3572
Max Act: 2.3244. Min Act: -0.1700
Data Index: 3427493 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3572. Min Range: -2.3572
Max Act: 2.3079. Min Act: -0.1699
Data Index: 5427312 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3572. Min Range: -2.3572
Max Act: 2.2915. Min Act: -0.1700
Data Index: 562472 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3572. Min Range: -2.3572
Max Act: 2.2750. Min Act: -0.1699
Data Index: 3427499 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3572. Min Range: -2.3572
Max Act: 2.2915. Min Act: -0.1700
Data Index: 6718262 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3572. Min Range: -2.3572
Max Act: 2.2089. Min Act: -0.1700
Data Index: 1193500 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3572. Min Range: -2.3572
Max Act: 2.2089. Min Act: -0.1700
Data Index: 7310691 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3572. Min Range: -2.3572
Max Act: 2.1923. Min Act: -0.1700
Data Index: 6400866 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3572. Min Range: -2.3572
Max Act: 2.1923. Min Act: -0.1687
Data Index: 6057920 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3572. Min Range: -2.3572
Max Act: 2.2089. Min Act: -0.1700
Data Index: 4403574 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3572. Min Range: -2.3572
Max Act: 2.2089. Min Act: -0.1699
Data Index: 3427503 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3572. Min Range: -2.3572
Max Act: 2.1757. Min Act: -0.1700
Data Index: 438003 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3572. Min Range: -2.3572
Max Act: 2.1757. Min Act: -0.1700
Data Index: 3746713 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3572. Min Range: -2.3572
Max Act: 2.1757. Min Act: -0.1698
Data Index: 3746709 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3572. Min Range: -2.3572
Max Act: 2.1757. Min Act: -0.1693
Data Index: 5858493 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3572. Min Range: -2.3572
Max Act: 2.1590. Min Act: -0.1700
Data Index: 3746707 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3572. Min Range: -2.3572
Max Act: 2.1590. Min Act: -0.1687
Data Index: 6718264 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3572. Min Range: -2.3572
Max Act: 2.1590. Min Act: -0.1687
Data Index: 3427504 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #19