Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2554 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.5035. Min Range: -2.5035
Max Act: 2.5035. Min Act: -0.1700
Data Index: 4426440 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5035. Min Range: -2.5035
Max Act: 2.4548. Min Act: -0.1700
Data Index: 4426441 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5035. Min Range: -2.5035
Max Act: 2.4386. Min Act: -0.1700
Data Index: 8324063 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5035. Min Range: -2.5035
Max Act: 2.2252. Min Act: -0.1700
Data Index: 6615300 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5035. Min Range: -2.5035
Max Act: 2.2087. Min Act: -0.1700
Data Index: 675631 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5035. Min Range: -2.5035
Max Act: 2.1754. Min Act: -0.1700
Data Index: 5657472 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5035. Min Range: -2.5035
Max Act: 2.1754. Min Act: -0.1700
Data Index: 676439 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5035. Min Range: -2.5035
Max Act: 2.1254. Min Act: -0.1700
Data Index: 8070297 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5035. Min Range: -2.5035
Max Act: 2.1421. Min Act: -0.1700
Data Index: 675632 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5035. Min Range: -2.5035
Max Act: 2.1254. Min Act: -0.1700
Data Index: 846045 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5035. Min Range: -2.5035
Max Act: 2.1254. Min Act: -0.1700
Data Index: 7685102 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5035. Min Range: -2.5035
Max Act: 2.0920. Min Act: -0.1683
Data Index: 491443 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5035. Min Range: -2.5035
Max Act: 2.0920. Min Act: -0.1700
Data Index: 997754 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5035. Min Range: -2.5035
Max Act: 2.0920. Min Act: -0.1700
Data Index: 8474071 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5035. Min Range: -2.5035
Max Act: 2.0752. Min Act: -0.1700
Data Index: 5853832 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5035. Min Range: -2.5035
Max Act: 2.0752. Min Act: -0.1700
Data Index: 7183338 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5035. Min Range: -2.5035
Max Act: 2.0752. Min Act: -0.1700
Data Index: 3312321 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5035. Min Range: -2.5035
Max Act: 2.0584. Min Act: -0.1700
Data Index: 5922691 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5035. Min Range: -2.5035
Max Act: 2.0584. Min Act: -0.1700
Data Index: 8702374 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5035. Min Range: -2.5035
Max Act: 2.0584. Min Act: -0.1700
Data Index: 4641615 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #19