Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3303 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6840. Min Range: -7.6840
Max Act: 7.6840. Min Act: -0.1700
Data Index: 210328 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6840. Min Range: -7.6840
Max Act: 7.4340. Min Act: -0.1700
Data Index: 2127712 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6840. Min Range: -7.6840
Max Act: 7.3715. Min Act: -0.1700
Data Index: 4199809 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6840. Min Range: -7.6840
Max Act: 7.2152. Min Act: -0.1700
Data Index: 2413759 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6840. Min Range: -7.6840
Max Act: 7.1840. Min Act: -0.1700
Data Index: 7862497 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6840. Min Range: -7.6840
Max Act: 7.1840. Min Act: -0.1700
Data Index: 6885503 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6840. Min Range: -7.6840
Max Act: 7.1215. Min Act: -0.1700
Data Index: 438147 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6840. Min Range: -7.6840
Max Act: 7.1215. Min Act: -0.1700
Data Index: 101561 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6840. Min Range: -7.6840
Max Act: 7.0902. Min Act: -0.1700
Data Index: 4856676 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6840. Min Range: -7.6840
Max Act: 7.0277. Min Act: -0.1700
Data Index: 3408038 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6840. Min Range: -7.6840
Max Act: 7.0590. Min Act: -0.1700
Data Index: 8332866 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6840. Min Range: -7.6840
Max Act: 6.9965. Min Act: -0.1700
Data Index: 8531354 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6840. Min Range: -7.6840
Max Act: 7.0277. Min Act: -0.1700
Data Index: 2263544 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6840. Min Range: -7.6840
Max Act: 6.9652. Min Act: -0.1700
Data Index: 6668747 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6840. Min Range: -7.6840
Max Act: 6.9965. Min Act: -0.1700
Data Index: 3794724 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6840. Min Range: -7.6840
Max Act: 6.9652. Min Act: -0.1700
Data Index: 3138448 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6840. Min Range: -7.6840
Max Act: 6.9652. Min Act: -0.1700
Data Index: 7218374 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6840. Min Range: -7.6840
Max Act: 6.9652. Min Act: -0.1700
Data Index: 108247 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6840. Min Range: -7.6840
Max Act: 6.9965. Min Act: -0.1700
Data Index: 5667319 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6840. Min Range: -7.6840
Max Act: 6.9340. Min Act: -0.1700
Data Index: 8791596 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #19