Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3614 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.9806. Min Act: -0.1700
Data Index: 2302124 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.8869. Min Act: -0.1700
Data Index: 6878298 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.8556. Min Act: -0.1700
Data Index: 2569201 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.7306. Min Act: -0.1700
Data Index: 6878299 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.7306. Min Act: -0.1700
Data Index: 4380815 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.6994. Min Act: -0.1700
Data Index: 3239846 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.6994. Min Act: -0.1700
Data Index: 784691 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.6994. Min Act: -0.1700
Data Index: 1413046 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.6994. Min Act: -0.1700
Data Index: 5098952 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.6681. Min Act: -0.1700
Data Index: 427887 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.6369. Min Act: -0.1700
Data Index: 7105030 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.6056. Min Act: -0.1700
Data Index: 460696 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.6056. Min Act: -0.1700
Data Index: 4707070 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.6369. Min Act: -0.1700
Data Index: 2569204 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.6056. Min Act: -0.1700
Data Index: 4637895 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.6056. Min Act: -0.1700
Data Index: 480880 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.6369. Min Act: -0.1700
Data Index: 460692 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.6056. Min Act: -0.1700
Data Index: 6222832 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.5744. Min Act: -0.1700
Data Index: 5777768 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.5744. Min Act: -0.1700
Data Index: 3190723 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #19