Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6302 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2094. Min Range: -3.2094
Max Act: 3.2094. Min Act: -0.1700
Data Index: 8064115 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2094. Min Range: -3.2094
Max Act: 3.1149. Min Act: -0.1700
Data Index: 4493617 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2094. Min Range: -3.2094
Max Act: 3.1149. Min Act: -0.1700
Data Index: 5008816 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2094. Min Range: -3.2094
Max Act: 3.1149. Min Act: -0.1700
Data Index: 8167546 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2094. Min Range: -3.2094
Max Act: 3.1149. Min Act: -0.1700
Data Index: 8234582 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2094. Min Range: -3.2094
Max Act: 3.0676. Min Act: -0.1700
Data Index: 5057681 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2094. Min Range: -3.2094
Max Act: 3.0361. Min Act: -0.1700
Data Index: 2701386 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2094. Min Range: -3.2094
Max Act: 3.0361. Min Act: -0.1700
Data Index: 7997321 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2094. Min Range: -3.2094
Max Act: 3.0361. Min Act: -0.1700
Data Index: 603344 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2094. Min Range: -3.2094
Max Act: 3.0361. Min Act: -0.1700
Data Index: 1004019 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2094. Min Range: -3.2094
Max Act: 3.0361. Min Act: -0.1700
Data Index: 827470 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2094. Min Range: -3.2094
Max Act: 3.0203. Min Act: -0.1700
Data Index: 2739721 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2094. Min Range: -3.2094
Max Act: 3.0203. Min Act: -0.1700
Data Index: 3491816 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2094. Min Range: -3.2094
Max Act: 3.0203. Min Act: -0.1700
Data Index: 7441133 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2094. Min Range: -3.2094
Max Act: 3.0203. Min Act: -0.1700
Data Index: 880135 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2094. Min Range: -3.2094
Max Act: 3.0203. Min Act: -0.1700
Data Index: 8140466 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2094. Min Range: -3.2094
Max Act: 3.0045. Min Act: -0.1700
Data Index: 6350624 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2094. Min Range: -3.2094
Max Act: 3.0045. Min Act: -0.1700
Data Index: 2701385 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2094. Min Range: -3.2094
Max Act: 3.0045. Min Act: -0.1700
Data Index: 114709 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2094. Min Range: -3.2094
Max Act: 3.0045. Min Act: -0.1700
Data Index: 55019 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19