Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3183 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4054. Min Range: -9.4054
Max Act: 9.4054. Min Act: -0.1700
Data Index: 1775146 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4054. Min Range: -9.4054
Max Act: 8.6554. Min Act: -0.1700
Data Index: 364906 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4054. Min Range: -9.4054
Max Act: 8.6554. Min Act: -0.1700
Data Index: 5888785 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4054. Min Range: -9.4054
Max Act: 8.6554. Min Act: -0.1700
Data Index: 4117047 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4054. Min Range: -9.4054
Max Act: 8.6554. Min Act: -0.1700
Data Index: 3477208 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4054. Min Range: -9.4054
Max Act: 8.5929. Min Act: -0.1700
Data Index: 2120766 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4054. Min Range: -9.4054
Max Act: 8.4054. Min Act: -0.1700
Data Index: 5612474 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4054. Min Range: -9.4054
Max Act: 8.2804. Min Act: -0.1700
Data Index: 5435831 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4054. Min Range: -9.4054
Max Act: 8.2804. Min Act: -0.1700
Data Index: 8827209 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4054. Min Range: -9.4054
Max Act: 8.2804. Min Act: -0.1700
Data Index: 6585986 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4054. Min Range: -9.4054
Max Act: 8.2179. Min Act: -0.1700
Data Index: 2531362 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4054. Min Range: -9.4054
Max Act: 8.2179. Min Act: -0.1700
Data Index: 7547872 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4054. Min Range: -9.4054
Max Act: 8.2179. Min Act: -0.1700
Data Index: 4027385 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4054. Min Range: -9.4054
Max Act: 8.2179. Min Act: -0.1700
Data Index: 8788218 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4054. Min Range: -9.4054
Max Act: 8.1554. Min Act: -0.1700
Data Index: 4109593 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4054. Min Range: -9.4054
Max Act: 8.0617. Min Act: -0.1700
Data Index: 6442341 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4054. Min Range: -9.4054
Max Act: 8.0304. Min Act: -0.1700
Data Index: 4574206 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4054. Min Range: -9.4054
Max Act: 7.9992. Min Act: -0.1700
Data Index: 8278436 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4054. Min Range: -9.4054
Max Act: 7.9679. Min Act: -0.1700
Data Index: 8085095 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4054. Min Range: -9.4054
Max Act: 7.8742. Min Act: -0.1700
Data Index: 6644147 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #19