Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1961 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8730. Min Range: -6.8730
Max Act: 6.8730. Min Act: -0.1700
Data Index: 2024173 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8730. Min Range: -6.8730
Max Act: 6.7480. Min Act: -0.1700
Data Index: 7492817 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8730. Min Range: -6.8730
Max Act: 6.5605. Min Act: -0.1700
Data Index: 4915799 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8730. Min Range: -6.8730
Max Act: 6.2793. Min Act: -0.1700
Data Index: 6093326 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8730. Min Range: -6.8730
Max Act: 6.2168. Min Act: -0.1700
Data Index: 4978746 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8730. Min Range: -6.8730
Max Act: 6.1855. Min Act: -0.1700
Data Index: 543182 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8730. Min Range: -6.8730
Max Act: 6.1855. Min Act: -0.1700
Data Index: 4739036 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8730. Min Range: -6.8730
Max Act: 6.1855. Min Act: -0.1700
Data Index: 4896296 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8730. Min Range: -6.8730
Max Act: 6.1855. Min Act: -0.1700
Data Index: 2559765 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8730. Min Range: -6.8730
Max Act: 6.1855. Min Act: -0.1700
Data Index: 6093339 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8730. Min Range: -6.8730
Max Act: 6.2168. Min Act: -0.1700
Data Index: 1765994 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8730. Min Range: -6.8730
Max Act: 6.1543. Min Act: -0.1700
Data Index: 4205623 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8730. Min Range: -6.8730
Max Act: 6.1230. Min Act: -0.1700
Data Index: 5584152 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8730. Min Range: -6.8730
Max Act: 6.1230. Min Act: -0.1700
Data Index: 4078827 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8730. Min Range: -6.8730
Max Act: 6.0918. Min Act: -0.1700
Data Index: 1268282 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8730. Min Range: -6.8730
Max Act: 6.0918. Min Act: -0.1700
Data Index: 3350803 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8730. Min Range: -6.8730
Max Act: 6.0918. Min Act: -0.1700
Data Index: 6031119 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8730. Min Range: -6.8730
Max Act: 6.0918. Min Act: -0.1700
Data Index: 4978744 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8730. Min Range: -6.8730
Max Act: 6.0918. Min Act: -0.1700
Data Index: 7132771 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8730. Min Range: -6.8730
Max Act: 6.0918. Min Act: -0.1700
Data Index: 371031 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #19