Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2363 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.6078. Min Range: -7.6078
Max Act: 7.6078. Min Act: -0.1700
Data Index: 5937314 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6078. Min Range: -7.6078
Max Act: 7.5765. Min Act: -0.1700
Data Index: 543178 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6078. Min Range: -7.6078
Max Act: 7.5140. Min Act: -0.1700
Data Index: 6760461 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6078. Min Range: -7.6078
Max Act: 7.4203. Min Act: -0.1700
Data Index: 5263879 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6078. Min Range: -7.6078
Max Act: 7.3578. Min Act: -0.1700
Data Index: 7366525 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6078. Min Range: -7.6078
Max Act: 7.3265. Min Act: -0.1700
Data Index: 4175234 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6078. Min Range: -7.6078
Max Act: 7.3265. Min Act: -0.1700
Data Index: 8609982 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6078. Min Range: -7.6078
Max Act: 7.2015. Min Act: -0.1700
Data Index: 2472381 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6078. Min Range: -7.6078
Max Act: 7.1703. Min Act: -0.1700
Data Index: 1655353 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6078. Min Range: -7.6078
Max Act: 7.1390. Min Act: -0.1700
Data Index: 4880202 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6078. Min Range: -7.6078
Max Act: 7.1078. Min Act: -0.1700
Data Index: 6454286 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6078. Min Range: -7.6078
Max Act: 7.0765. Min Act: -0.1700
Data Index: 2830671 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6078. Min Range: -7.6078
Max Act: 7.0765. Min Act: -0.1700
Data Index: 3193317 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6078. Min Range: -7.6078
Max Act: 7.0140. Min Act: -0.1700
Data Index: 3609518 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6078. Min Range: -7.6078
Max Act: 7.0140. Min Act: -0.1700
Data Index: 6022896 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6078. Min Range: -7.6078
Max Act: 7.0140. Min Act: -0.1700
Data Index: 5390584 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6078. Min Range: -7.6078
Max Act: 6.9828. Min Act: -0.1700
Data Index: 8108695 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6078. Min Range: -7.6078
Max Act: 6.9515. Min Act: -0.1700
Data Index: 6570198 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6078. Min Range: -7.6078
Max Act: 6.9828. Min Act: -0.1700
Data Index: 2062369 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6078. Min Range: -7.6078
Max Act: 6.9515. Min Act: -0.1700
Data Index: 389359 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #19