Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2516 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0174. Min Range: -4.0174
Max Act: 4.0174. Min Act: -0.1700
Data Index: 3755085 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0174. Min Range: -4.0174
Max Act: 3.8767. Min Act: -0.1700
Data Index: 5570480 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0174. Min Range: -4.0174
Max Act: 3.8767. Min Act: -0.1700
Data Index: 3008993 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0174. Min Range: -4.0174
Max Act: 3.8610. Min Act: -0.1700
Data Index: 2698059 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0174. Min Range: -4.0174
Max Act: 3.8610. Min Act: -0.1700
Data Index: 5638498 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0174. Min Range: -4.0174
Max Act: 3.8454. Min Act: -0.1700
Data Index: 5193859 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0174. Min Range: -4.0174
Max Act: 3.8298. Min Act: -0.1700
Data Index: 5621167 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0174. Min Range: -4.0174
Max Act: 3.7985. Min Act: -0.1700
Data Index: 8141789 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0174. Min Range: -4.0174
Max Act: 3.7985. Min Act: -0.1700
Data Index: 6244541 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0174. Min Range: -4.0174
Max Act: 3.7829. Min Act: -0.1700
Data Index: 4340712 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0174. Min Range: -4.0174
Max Act: 3.7672. Min Act: -0.1700
Data Index: 851101 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0174. Min Range: -4.0174
Max Act: 3.7672. Min Act: -0.1700
Data Index: 5858888 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0174. Min Range: -4.0174
Max Act: 3.7672. Min Act: -0.1700
Data Index: 6459497 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0174. Min Range: -4.0174
Max Act: 3.7516. Min Act: -0.1700
Data Index: 489730 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0174. Min Range: -4.0174
Max Act: 3.7359. Min Act: -0.1700
Data Index: 2640720 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0174. Min Range: -4.0174
Max Act: 3.7359. Min Act: -0.1700
Data Index: 5159660 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0174. Min Range: -4.0174
Max Act: 3.7516. Min Act: -0.1700
Data Index: 6763833 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0174. Min Range: -4.0174
Max Act: 3.7359. Min Act: -0.1700
Data Index: 2021602 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0174. Min Range: -4.0174
Max Act: 3.7203. Min Act: -0.1700
Data Index: 6638949 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0174. Min Range: -4.0174
Max Act: 3.7203. Min Act: -0.1700
Data Index: 6282373 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #19