Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2918 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7278. Min Range: -3.7278
Max Act: 3.7278. Min Act: -0.1700
Data Index: 6651418 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7278. Min Range: -3.7278
Max Act: 3.7122. Min Act: -0.1700
Data Index: 172909 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7278. Min Range: -3.7278
Max Act: 3.5557. Min Act: -0.1700
Data Index: 4105271 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7278. Min Range: -3.7278
Max Act: 3.5557. Min Act: -0.1700
Data Index: 2162278 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7278. Min Range: -3.7278
Max Act: 3.5087. Min Act: -0.1700
Data Index: 8495853 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7278. Min Range: -3.7278
Max Act: 3.4617. Min Act: -0.1700
Data Index: 2475942 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7278. Min Range: -3.7278
Max Act: 3.4461. Min Act: -0.1700
Data Index: 3901956 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7278. Min Range: -3.7278
Max Act: 3.4304. Min Act: -0.1700
Data Index: 3520734 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7278. Min Range: -3.7278
Max Act: 3.3990. Min Act: -0.1700
Data Index: 7435 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7278. Min Range: -3.7278
Max Act: 3.4147. Min Act: -0.1700
Data Index: 1613669 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7278. Min Range: -3.7278
Max Act: 3.3990. Min Act: -0.1700
Data Index: 7155784 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7278. Min Range: -3.7278
Max Act: 3.3990. Min Act: -0.1700
Data Index: 538289 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7278. Min Range: -3.7278
Max Act: 3.3834. Min Act: -0.1700
Data Index: 3684608 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7278. Min Range: -3.7278
Max Act: 3.3834. Min Act: -0.1700
Data Index: 1436163 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7278. Min Range: -3.7278
Max Act: 3.3677. Min Act: -0.1700
Data Index: 1586742 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7278. Min Range: -3.7278
Max Act: 3.3677. Min Act: -0.1700
Data Index: 3587183 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7278. Min Range: -3.7278
Max Act: 3.3834. Min Act: -0.1700
Data Index: 8261906 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7278. Min Range: -3.7278
Max Act: 3.3677. Min Act: -0.1700
Data Index: 5341596 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7278. Min Range: -3.7278
Max Act: 3.3677. Min Act: -0.1700
Data Index: 7689080 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7278. Min Range: -3.7278
Max Act: 3.3677. Min Act: -0.1700
Data Index: 4652272 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #19