Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5836 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9642. Min Range: -5.9642
Max Act: 5.9642. Min Act: -0.1700
Data Index: 8186698 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9642. Min Range: -5.9642
Max Act: 5.8704. Min Act: -0.1700
Data Index: 8565536 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9642. Min Range: -5.9642
Max Act: 5.8704. Min Act: -0.1700
Data Index: 2766281 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9642. Min Range: -5.9642
Max Act: 5.7767. Min Act: -0.1700
Data Index: 8552158 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9642. Min Range: -5.9642
Max Act: 5.7454. Min Act: -0.1700
Data Index: 7878216 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9642. Min Range: -5.9642
Max Act: 5.6517. Min Act: -0.1700
Data Index: 2124253 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9642. Min Range: -5.9642
Max Act: 5.5892. Min Act: -0.1700
Data Index: 1067402 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9642. Min Range: -5.9642
Max Act: 5.6204. Min Act: -0.1700
Data Index: 7343314 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9642. Min Range: -5.9642
Max Act: 5.6204. Min Act: -0.1700
Data Index: 4320847 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9642. Min Range: -5.9642
Max Act: 5.5579. Min Act: -0.1700
Data Index: 5710580 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9642. Min Range: -5.9642
Max Act: 5.5267. Min Act: -0.1700
Data Index: 6470812 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9642. Min Range: -5.9642
Max Act: 5.5579. Min Act: -0.1700
Data Index: 5709648 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9642. Min Range: -5.9642
Max Act: 5.4642. Min Act: -0.1700
Data Index: 3633263 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9642. Min Range: -5.9642
Max Act: 5.4642. Min Act: -0.1700
Data Index: 7144032 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9642. Min Range: -5.9642
Max Act: 5.4954. Min Act: -0.1700
Data Index: 3633260 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9642. Min Range: -5.9642
Max Act: 5.4329. Min Act: -0.1700
Data Index: 1963144 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9642. Min Range: -5.9642
Max Act: 5.4642. Min Act: -0.1700
Data Index: 427864 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9642. Min Range: -5.9642
Max Act: 5.4017. Min Act: -0.1700
Data Index: 6530960 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9642. Min Range: -5.9642
Max Act: 5.4017. Min Act: -0.1700
Data Index: 2738657 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9642. Min Range: -5.9642
Max Act: 5.4017. Min Act: -0.1700
Data Index: 193842 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #19