Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3792 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1954. Min Range: -6.1954
Max Act: 6.1954. Min Act: -0.1700
Data Index: 4644163 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1954. Min Range: -6.1954
Max Act: 6.1017. Min Act: -0.1700
Data Index: 3209339 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1954. Min Range: -6.1954
Max Act: 6.0079. Min Act: -0.1700
Data Index: 8441035 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1954. Min Range: -6.1954
Max Act: 5.9767. Min Act: -0.1700
Data Index: 6813879 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1954. Min Range: -6.1954
Max Act: 5.8829. Min Act: -0.1700
Data Index: 5263407 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1954. Min Range: -6.1954
Max Act: 5.8517. Min Act: -0.1700
Data Index: 1324959 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1954. Min Range: -6.1954
Max Act: 5.8204. Min Act: -0.1700
Data Index: 3183813 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1954. Min Range: -6.1954
Max Act: 5.8517. Min Act: -0.1700
Data Index: 1551702 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1954. Min Range: -6.1954
Max Act: 5.8517. Min Act: -0.1700
Data Index: 4873934 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1954. Min Range: -6.1954
Max Act: 5.7892. Min Act: -0.1700
Data Index: 505455 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1954. Min Range: -6.1954
Max Act: 5.8204. Min Act: -0.1700
Data Index: 4568195 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1954. Min Range: -6.1954
Max Act: 5.7892. Min Act: -0.1700
Data Index: 6316914 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1954. Min Range: -6.1954
Max Act: 5.7267. Min Act: -0.1700
Data Index: 7178815 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1954. Min Range: -6.1954
Max Act: 5.6954. Min Act: -0.1700
Data Index: 1446860 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1954. Min Range: -6.1954
Max Act: 5.6017. Min Act: -0.1700
Data Index: 242498 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1954. Min Range: -6.1954
Max Act: 5.6329. Min Act: -0.1700
Data Index: 2171546 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1954. Min Range: -6.1954
Max Act: 5.6017. Min Act: -0.1700
Data Index: 2808393 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1954. Min Range: -6.1954
Max Act: 5.6017. Min Act: -0.1700
Data Index: 496412 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1954. Min Range: -6.1954
Max Act: 5.6329. Min Act: -0.1700
Data Index: 376985 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1954. Min Range: -6.1954
Max Act: 5.6017. Min Act: -0.1700
Data Index: 7037762 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #19