Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4118 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.0974. Min Range: -1.0974
Max Act: 1.0974. Min Act: -0.1699
Data Index: 5750478 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0974. Min Range: -1.0974
Max Act: 1.0450. Min Act: -0.1700
Data Index: 198122 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0974. Min Range: -1.0974
Max Act: 1.0275. Min Act: -0.1700
Data Index: 6472632 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0974. Min Range: -1.0974
Max Act: 1.0101. Min Act: -0.1700
Data Index: 7289760 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0974. Min Range: -1.0974
Max Act: 1.0101. Min Act: -0.1699
Data Index: 3216575 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0974. Min Range: -1.0974
Max Act: 0.9928. Min Act: -0.1700
Data Index: 3822432 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0974. Min Range: -1.0974
Max Act: 0.9496. Min Act: -0.1700
Data Index: 8291504 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0974. Min Range: -1.0974
Max Act: 0.9237. Min Act: -0.1700
Data Index: 1187297 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0974. Min Range: -1.0974
Max Act: 0.8895. Min Act: -0.1698
Data Index: 7298669 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0974. Min Range: -1.0974
Max Act: 0.8980. Min Act: -0.1700
Data Index: 3560586 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0974. Min Range: -1.0974
Max Act: 0.8639. Min Act: -0.1700
Data Index: 6276707 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0974. Min Range: -1.0974
Max Act: 0.8810. Min Act: -0.1700
Data Index: 3999602 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0974. Min Range: -1.0974
Max Act: 0.8639. Min Act: -0.1700
Data Index: 8143801 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0974. Min Range: -1.0974
Max Act: 0.8639. Min Act: -0.1700
Data Index: 6244739 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0974. Min Range: -1.0974
Max Act: 0.8724. Min Act: -0.1700
Data Index: 2385951 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0974. Min Range: -1.0974
Max Act: 0.8554. Min Act: -0.1700
Data Index: 5970202 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0974. Min Range: -1.0974
Max Act: 0.8639. Min Act: -0.1697
Data Index: 7262217 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0974. Min Range: -1.0974
Max Act: 0.8470. Min Act: -0.1700
Data Index: 4353196 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0974. Min Range: -1.0974
Max Act: 0.8216. Min Act: -0.1700
Data Index: 6243930 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0974. Min Range: -1.0974
Max Act: 0.8385. Min Act: -0.1700
Data Index: 3855953 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #19