Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4946 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7016. Min Range: -6.7016
Max Act: 6.7016. Min Act: -0.1700
Data Index: 770769 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7016. Min Range: -6.7016
Max Act: 6.5766. Min Act: -0.1700
Data Index: 15603 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7016. Min Range: -6.7016
Max Act: 6.3891. Min Act: -0.1700
Data Index: 234094 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7016. Min Range: -6.7016
Max Act: 6.3578. Min Act: -0.1700
Data Index: 6941233 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7016. Min Range: -6.7016
Max Act: 6.3578. Min Act: -0.1700
Data Index: 2735055 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7016. Min Range: -6.7016
Max Act: 6.3578. Min Act: -0.1700
Data Index: 2472559 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7016. Min Range: -6.7016
Max Act: 6.2641. Min Act: -0.1700
Data Index: 5970576 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7016. Min Range: -6.7016
Max Act: 6.2641. Min Act: -0.1700
Data Index: 5975073 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7016. Min Range: -6.7016
Max Act: 6.2328. Min Act: -0.1700
Data Index: 7491967 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7016. Min Range: -6.7016
Max Act: 6.2328. Min Act: -0.1700
Data Index: 4088483 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7016. Min Range: -6.7016
Max Act: 6.2016. Min Act: -0.1700
Data Index: 1191593 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7016. Min Range: -6.7016
Max Act: 6.1703. Min Act: -0.1700
Data Index: 6175453 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7016. Min Range: -6.7016
Max Act: 6.1391. Min Act: -0.1700
Data Index: 7577930 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7016. Min Range: -6.7016
Max Act: 6.1391. Min Act: -0.1700
Data Index: 6538181 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7016. Min Range: -6.7016
Max Act: 6.1078. Min Act: -0.1700
Data Index: 4707169 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7016. Min Range: -6.7016
Max Act: 6.1391. Min Act: -0.1700
Data Index: 5847815 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7016. Min Range: -6.7016
Max Act: 6.1078. Min Act: -0.1700
Data Index: 6793337 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7016. Min Range: -6.7016
Max Act: 6.1078. Min Act: -0.1700
Data Index: 3299126 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7016. Min Range: -6.7016
Max Act: 6.1078. Min Act: -0.1700
Data Index: 5980781 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7016. Min Range: -6.7016
Max Act: 6.1078. Min Act: -0.1700
Data Index: 6014961 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #19