Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3886 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 14.0789. Min Range: -14.0789
Max Act: 14.0789. Min Act: -0.1700
Data Index: 2550635 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.0789. Min Range: -14.0789
Max Act: 13.9539. Min Act: -0.1700
Data Index: 6436395 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.0789. Min Range: -14.0789
Max Act: 13.9539. Min Act: -0.1700
Data Index: 8735783 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.0789. Min Range: -14.0789
Max Act: 13.9539. Min Act: -0.1700
Data Index: 1864039 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.0789. Min Range: -14.0789
Max Act: 13.8289. Min Act: -0.1700
Data Index: 430145 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.0789. Min Range: -14.0789
Max Act: 13.7664. Min Act: -0.1700
Data Index: 6751895 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.0789. Min Range: -14.0789
Max Act: 13.7039. Min Act: -0.1700
Data Index: 8577171 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.0789. Min Range: -14.0789
Max Act: 13.7039. Min Act: -0.1700
Data Index: 40673 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.0789. Min Range: -14.0789
Max Act: 13.6414. Min Act: -0.1700
Data Index: 1672206 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.0789. Min Range: -14.0789
Max Act: 13.6414. Min Act: -0.1700
Data Index: 4065687 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.0789. Min Range: -14.0789
Max Act: 13.5789. Min Act: -0.1700
Data Index: 633217 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.0789. Min Range: -14.0789
Max Act: 13.5164. Min Act: -0.1700
Data Index: 1476330 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.0789. Min Range: -14.0789
Max Act: 13.6414. Min Act: -0.1700
Data Index: 15314 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.0789. Min Range: -14.0789
Max Act: 13.5789. Min Act: -0.1700
Data Index: 6217708 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.0789. Min Range: -14.0789
Max Act: 13.5789. Min Act: -0.1700
Data Index: 127514 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.0789. Min Range: -14.0789
Max Act: 13.5789. Min Act: -0.1700
Data Index: 3985567 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.0789. Min Range: -14.0789
Max Act: 13.5164. Min Act: -0.1700
Data Index: 7367864 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.0789. Min Range: -14.0789
Max Act: 13.5164. Min Act: -0.1700
Data Index: 6226721 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.0789. Min Range: -14.0789
Max Act: 13.5164. Min Act: -0.1700
Data Index: 6481993 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.0789. Min Range: -14.0789
Max Act: 13.5164. Min Act: -0.1700
Data Index: 6420426 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #19