Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3745 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4266. Min Range: -4.4266
Max Act: 4.4266. Min Act: -0.1700
Data Index: 8516988 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4266. Min Range: -4.4266
Max Act: 4.3016. Min Act: -0.1700
Data Index: 4677593 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4266. Min Range: -4.4266
Max Act: 4.2391. Min Act: -0.1700
Data Index: 1530740 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4266. Min Range: -4.4266
Max Act: 4.2391. Min Act: -0.1700
Data Index: 8418276 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4266. Min Range: -4.4266
Max Act: 4.2391. Min Act: -0.1700
Data Index: 7962805 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4266. Min Range: -4.4266
Max Act: 4.2078. Min Act: -0.1700
Data Index: 3854695 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4266. Min Range: -4.4266
Max Act: 4.2078. Min Act: -0.1700
Data Index: 6531590 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4266. Min Range: -4.4266
Max Act: 4.1141. Min Act: -0.1700
Data Index: 4208430 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4266. Min Range: -4.4266
Max Act: 4.1453. Min Act: -0.1700
Data Index: 3780357 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4266. Min Range: -4.4266
Max Act: 4.0828. Min Act: -0.1700
Data Index: 1195210 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4266. Min Range: -4.4266
Max Act: 4.0203. Min Act: -0.1700
Data Index: 8262698 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4266. Min Range: -4.4266
Max Act: 4.0203. Min Act: -0.1700
Data Index: 5927512 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4266. Min Range: -4.4266
Max Act: 3.9890. Min Act: -0.1700
Data Index: 4378660 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4266. Min Range: -4.4266
Max Act: 3.9578. Min Act: -0.1700
Data Index: 930032 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4266. Min Range: -4.4266
Max Act: 3.9578. Min Act: -0.1700
Data Index: 3274672 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4266. Min Range: -4.4266
Max Act: 3.9578. Min Act: -0.1700
Data Index: 3248658 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4266. Min Range: -4.4266
Max Act: 3.9578. Min Act: -0.1700
Data Index: 3974082 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4266. Min Range: -4.4266
Max Act: 3.9265. Min Act: -0.1700
Data Index: 512493 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4266. Min Range: -4.4266
Max Act: 3.9265. Min Act: -0.1700
Data Index: 6374625 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4266. Min Range: -4.4266
Max Act: 3.9265. Min Act: -0.1700
Data Index: 3361298 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #19