Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3154 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1823. Min Range: -3.1823
Max Act: 3.1823. Min Act: -0.1700
Data Index: 3201629 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1823. Min Range: -3.1823
Max Act: 3.1665. Min Act: -0.1700
Data Index: 1098474 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1823. Min Range: -3.1823
Max Act: 3.1665. Min Act: -0.1700
Data Index: 4162568 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1823. Min Range: -3.1823
Max Act: 3.1193. Min Act: -0.1700
Data Index: 3281425 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1823. Min Range: -3.1823
Max Act: 3.1350. Min Act: -0.1700
Data Index: 1112281 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1823. Min Range: -3.1823
Max Act: 3.1508. Min Act: -0.1700
Data Index: 1191542 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1823. Min Range: -3.1823
Max Act: 3.1193. Min Act: -0.1700
Data Index: 5056937 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1823. Min Range: -3.1823
Max Act: 3.1193. Min Act: -0.1700
Data Index: 1995513 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1823. Min Range: -3.1823
Max Act: 3.1193. Min Act: -0.1700
Data Index: 76340 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1823. Min Range: -3.1823
Max Act: 3.1193. Min Act: -0.1700
Data Index: 2568712 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1823. Min Range: -3.1823
Max Act: 3.0720. Min Act: -0.1700
Data Index: 3201634 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1823. Min Range: -3.1823
Max Act: 3.0720. Min Act: -0.1700
Data Index: 7847510 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1823. Min Range: -3.1823
Max Act: 3.0720. Min Act: -0.1700
Data Index: 1676978 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1823. Min Range: -3.1823
Max Act: 3.0562. Min Act: -0.1700
Data Index: 2805834 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1823. Min Range: -3.1823
Max Act: 3.0404. Min Act: -0.1700
Data Index: 7438486 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1823. Min Range: -3.1823
Max Act: 3.0089. Min Act: -0.1700
Data Index: 2209733 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1823. Min Range: -3.1823
Max Act: 2.9931. Min Act: -0.1700
Data Index: 387524 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1823. Min Range: -3.1823
Max Act: 2.9931. Min Act: -0.1700
Data Index: 1689572 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1823. Min Range: -3.1823
Max Act: 2.9772. Min Act: -0.1700
Data Index: 6348169 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1823. Min Range: -3.1823
Max Act: 2.9456. Min Act: -0.1700
Data Index: 1058161 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #19