Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2390 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7116. Min Range: -2.7116
Max Act: 2.7116. Min Act: -0.1700
Data Index: 8378348 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7116. Min Range: -2.7116
Max Act: 2.6636. Min Act: -0.1700
Data Index: 2563307 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7116. Min Range: -2.7116
Max Act: 2.5348. Min Act: -0.1700
Data Index: 3195019 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7116. Min Range: -2.7116
Max Act: 2.5024. Min Act: -0.1700
Data Index: 1348517 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7116. Min Range: -2.7116
Max Act: 2.5186. Min Act: -0.1700
Data Index: 2986974 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7116. Min Range: -2.7116
Max Act: 2.5024. Min Act: -0.1700
Data Index: 362832 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7116. Min Range: -2.7116
Max Act: 2.5024. Min Act: -0.1700
Data Index: 7863000 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7116. Min Range: -2.7116
Max Act: 2.5024. Min Act: -0.1700
Data Index: 4239611 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7116. Min Range: -2.7116
Max Act: 2.4862. Min Act: -0.1700
Data Index: 5053281 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7116. Min Range: -2.7116
Max Act: 2.4538. Min Act: -0.1700
Data Index: 6165920 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7116. Min Range: -2.7116
Max Act: 2.4538. Min Act: -0.1700
Data Index: 4112735 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7116. Min Range: -2.7116
Max Act: 2.4375. Min Act: -0.1700
Data Index: 6993536 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7116. Min Range: -2.7116
Max Act: 2.4375. Min Act: -0.1700
Data Index: 7116917 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7116. Min Range: -2.7116
Max Act: 2.4049. Min Act: -0.1700
Data Index: 1850109 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7116. Min Range: -2.7116
Max Act: 2.4375. Min Act: -0.1700
Data Index: 1418125 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7116. Min Range: -2.7116
Max Act: 2.4212. Min Act: -0.1700
Data Index: 4787060 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7116. Min Range: -2.7116
Max Act: 2.4212. Min Act: -0.1700
Data Index: 7059250 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7116. Min Range: -2.7116
Max Act: 2.3886. Min Act: -0.1700
Data Index: 3468367 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7116. Min Range: -2.7116
Max Act: 2.4049. Min Act: -0.1700
Data Index: 5053278 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7116. Min Range: -2.7116
Max Act: 2.4049. Min Act: -0.1700
Data Index: 2116069 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #19