Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 998 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3078. Min Range: -5.3078
Max Act: 5.3078. Min Act: -0.1700
Data Index: 7127392 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3078. Min Range: -5.3078
Max Act: 5.2453. Min Act: -0.1700
Data Index: 5738553 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3078. Min Range: -5.3078
Max Act: 5.1203. Min Act: -0.1700
Data Index: 2059565 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3078. Min Range: -5.3078
Max Act: 5.0890. Min Act: -0.1700
Data Index: 7000916 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3078. Min Range: -5.3078
Max Act: 5.1203. Min Act: -0.1700
Data Index: 2253561 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3078. Min Range: -5.3078
Max Act: 5.1203. Min Act: -0.1700
Data Index: 4265831 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3078. Min Range: -5.3078
Max Act: 5.0890. Min Act: -0.1700
Data Index: 5551978 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3078. Min Range: -5.3078
Max Act: 5.0890. Min Act: -0.1700
Data Index: 726817 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3078. Min Range: -5.3078
Max Act: 5.0578. Min Act: -0.1700
Data Index: 8621738 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3078. Min Range: -5.3078
Max Act: 5.0265. Min Act: -0.1700
Data Index: 4857948 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3078. Min Range: -5.3078
Max Act: 5.0265. Min Act: -0.1700
Data Index: 477543 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3078. Min Range: -5.3078
Max Act: 5.0265. Min Act: -0.1700
Data Index: 6376777 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3078. Min Range: -5.3078
Max Act: 4.9640. Min Act: -0.1700
Data Index: 4454877 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3078. Min Range: -5.3078
Max Act: 4.9640. Min Act: -0.1700
Data Index: 655226 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3078. Min Range: -5.3078
Max Act: 4.9328. Min Act: -0.1700
Data Index: 5517553 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3078. Min Range: -5.3078
Max Act: 4.9640. Min Act: -0.1700
Data Index: 7039385 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3078. Min Range: -5.3078
Max Act: 4.9015. Min Act: -0.1700
Data Index: 6792258 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3078. Min Range: -5.3078
Max Act: 4.8703. Min Act: -0.1700
Data Index: 411965 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3078. Min Range: -5.3078
Max Act: 4.9015. Min Act: -0.1700
Data Index: 6686127 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3078. Min Range: -5.3078
Max Act: 4.8703. Min Act: -0.1700
Data Index: 2458724 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #19