Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5442 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3363. Min Range: -4.3363
Max Act: 4.3363. Min Act: -0.1700
Data Index: 6496817 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3363. Min Range: -4.3363
Max Act: 4.0862. Min Act: -0.1700
Data Index: 4889913 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3363. Min Range: -4.3363
Max Act: 3.9455. Min Act: -0.1700
Data Index: 1464380 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3363. Min Range: -4.3363
Max Act: 3.9299. Min Act: -0.1700
Data Index: 5484969 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3363. Min Range: -4.3363
Max Act: 3.7892. Min Act: -0.1700
Data Index: 1066262 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3363. Min Range: -4.3363
Max Act: 3.7736. Min Act: -0.1700
Data Index: 5269705 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3363. Min Range: -4.3363
Max Act: 3.7110. Min Act: -0.1700
Data Index: 8319049 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3363. Min Range: -4.3363
Max Act: 3.7110. Min Act: -0.1700
Data Index: 7903586 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3363. Min Range: -4.3363
Max Act: 3.6797. Min Act: -0.1700
Data Index: 4989106 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3363. Min Range: -4.3363
Max Act: 3.6954. Min Act: -0.1700
Data Index: 7509253 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3363. Min Range: -4.3363
Max Act: 3.6954. Min Act: -0.1700
Data Index: 573229 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3363. Min Range: -4.3363
Max Act: 3.6954. Min Act: -0.1700
Data Index: 8362547 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3363. Min Range: -4.3363
Max Act: 3.6954. Min Act: -0.1700
Data Index: 4151878 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3363. Min Range: -4.3363
Max Act: 3.6954. Min Act: -0.1700
Data Index: 8326921 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3363. Min Range: -4.3363
Max Act: 3.6797. Min Act: -0.1700
Data Index: 3725894 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3363. Min Range: -4.3363
Max Act: 3.6797. Min Act: -0.1700
Data Index: 6690271 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3363. Min Range: -4.3363
Max Act: 3.6641. Min Act: -0.1700
Data Index: 8693499 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3363. Min Range: -4.3363
Max Act: 3.6484. Min Act: -0.1700
Data Index: 933960 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3363. Min Range: -4.3363
Max Act: 3.6641. Min Act: -0.1700
Data Index: 2159481 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3363. Min Range: -4.3363
Max Act: 3.6641. Min Act: -0.1700
Data Index: 5101270 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #19