Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1742 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3097. Min Range: -3.3097
Max Act: 3.3097. Min Act: -0.1700
Data Index: 7100297 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3097. Min Range: -3.3097
Max Act: 3.2155. Min Act: -0.1700
Data Index: 5169012 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3097. Min Range: -3.3097
Max Act: 2.9948. Min Act: -0.1700
Data Index: 4032633 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3097. Min Range: -3.3097
Max Act: 2.9790. Min Act: -0.1700
Data Index: 5109610 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3097. Min Range: -3.3097
Max Act: 2.9790. Min Act: -0.1700
Data Index: 784765 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3097. Min Range: -3.3097
Max Act: 2.9632. Min Act: -0.1700
Data Index: 5214609 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3097. Min Range: -3.3097
Max Act: 2.9632. Min Act: -0.1700
Data Index: 4797140 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3097. Min Range: -3.3097
Max Act: 2.9315. Min Act: -0.1700
Data Index: 6663987 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3097. Min Range: -3.3097
Max Act: 2.9315. Min Act: -0.1700
Data Index: 7156758 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3097. Min Range: -3.3097
Max Act: 2.9157. Min Act: -0.1700
Data Index: 2151456 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3097. Min Range: -3.3097
Max Act: 2.9157. Min Act: -0.1700
Data Index: 2171520 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3097. Min Range: -3.3097
Max Act: 2.8840. Min Act: -0.1700
Data Index: 2422681 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3097. Min Range: -3.3097
Max Act: 2.8840. Min Act: -0.1700
Data Index: 7113571 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3097. Min Range: -3.3097
Max Act: 2.8998. Min Act: -0.1700
Data Index: 3424911 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3097. Min Range: -3.3097
Max Act: 2.8840. Min Act: -0.1700
Data Index: 4545069 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3097. Min Range: -3.3097
Max Act: 2.8681. Min Act: -0.1700
Data Index: 1814771 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3097. Min Range: -3.3097
Max Act: 2.8681. Min Act: -0.1700
Data Index: 8583470 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3097. Min Range: -3.3097
Max Act: 2.8840. Min Act: -0.1700
Data Index: 5348121 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3097. Min Range: -3.3097
Max Act: 2.8681. Min Act: -0.1700
Data Index: 3603228 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3097. Min Range: -3.3097
Max Act: 2.8363. Min Act: -0.1700
Data Index: 6892131 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #19