Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3587 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5932. Min Range: -3.5932
Max Act: 3.5932. Min Act: -0.1700
Data Index: 8526997 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5932. Min Range: -3.5932
Max Act: 3.2640. Min Act: -0.1700
Data Index: 4119260 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5932. Min Range: -3.5932
Max Act: 3.2483. Min Act: -0.1700
Data Index: 8733109 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5932. Min Range: -3.5932
Max Act: 3.2640. Min Act: -0.1700
Data Index: 7068169 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5932. Min Range: -3.5932
Max Act: 3.2326. Min Act: -0.1700
Data Index: 270934 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5932. Min Range: -3.5932
Max Act: 3.2326. Min Act: -0.1700
Data Index: 2162338 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5932. Min Range: -3.5932
Max Act: 3.2168. Min Act: -0.1700
Data Index: 3784627 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5932. Min Range: -3.5932
Max Act: 3.2011. Min Act: -0.1700
Data Index: 2555968 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5932. Min Range: -3.5932
Max Act: 3.1854. Min Act: -0.1700
Data Index: 1524118 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5932. Min Range: -3.5932
Max Act: 3.1539. Min Act: -0.1700
Data Index: 3209544 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5932. Min Range: -3.5932
Max Act: 3.1854. Min Act: -0.1700
Data Index: 2019908 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5932. Min Range: -3.5932
Max Act: 3.1697. Min Act: -0.1700
Data Index: 3764623 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5932. Min Range: -3.5932
Max Act: 3.1697. Min Act: -0.1700
Data Index: 6327120 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5932. Min Range: -3.5932
Max Act: 3.1539. Min Act: -0.1700
Data Index: 7282095 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5932. Min Range: -3.5932
Max Act: 3.1067. Min Act: -0.1700
Data Index: 8373168 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5932. Min Range: -3.5932
Max Act: 3.1067. Min Act: -0.1700
Data Index: 598100 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5932. Min Range: -3.5932
Max Act: 3.1067. Min Act: -0.1700
Data Index: 1826037 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5932. Min Range: -3.5932
Max Act: 3.1224. Min Act: -0.1700
Data Index: 2157257 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5932. Min Range: -3.5932
Max Act: 3.0909. Min Act: -0.1700
Data Index: 8343105 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5932. Min Range: -3.5932
Max Act: 3.0909. Min Act: -0.1700
Data Index: 5657555 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #19