Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4425 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3984. Min Range: -5.3984
Max Act: 5.3984. Min Act: -0.1700
Data Index: 22900 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3984. Min Range: -5.3984
Max Act: 5.3047. Min Act: -0.1700
Data Index: 2781681 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3984. Min Range: -5.3984
Max Act: 5.2734. Min Act: -0.1700
Data Index: 7066384 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3984. Min Range: -5.3984
Max Act: 5.2109. Min Act: -0.1700
Data Index: 6772196 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3984. Min Range: -5.3984
Max Act: 5.2109. Min Act: -0.1700
Data Index: 5072342 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3984. Min Range: -5.3984
Max Act: 5.1797. Min Act: -0.1700
Data Index: 5538874 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3984. Min Range: -5.3984
Max Act: 5.1797. Min Act: -0.1700
Data Index: 1987417 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3984. Min Range: -5.3984
Max Act: 5.1484. Min Act: -0.1700
Data Index: 2402467 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3984. Min Range: -5.3984
Max Act: 5.1172. Min Act: -0.1700
Data Index: 5107624 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3984. Min Range: -5.3984
Max Act: 5.1172. Min Act: -0.1700
Data Index: 6966705 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3984. Min Range: -5.3984
Max Act: 5.1172. Min Act: -0.1700
Data Index: 8378178 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3984. Min Range: -5.3984
Max Act: 5.0859. Min Act: -0.1700
Data Index: 8551191 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3984. Min Range: -5.3984
Max Act: 5.1172. Min Act: -0.1700
Data Index: 4755832 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3984. Min Range: -5.3984
Max Act: 5.1172. Min Act: -0.1700
Data Index: 6564490 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3984. Min Range: -5.3984
Max Act: 5.1484. Min Act: -0.1700
Data Index: 1709027 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3984. Min Range: -5.3984
Max Act: 5.0859. Min Act: -0.1700
Data Index: 7238196 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3984. Min Range: -5.3984
Max Act: 5.0859. Min Act: -0.1700
Data Index: 2339978 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3984. Min Range: -5.3984
Max Act: 5.0859. Min Act: -0.1700
Data Index: 6920853 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3984. Min Range: -5.3984
Max Act: 5.0859. Min Act: -0.1700
Data Index: 3521271 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3984. Min Range: -5.3984
Max Act: 5.0859. Min Act: -0.1700
Data Index: 6310650 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #19