Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1894 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8739. Min Range: -6.8739
Max Act: 6.8739. Min Act: -0.1700
Data Index: 549568 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8739. Min Range: -6.8739
Max Act: 6.6551. Min Act: -0.1700
Data Index: 2611523 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8739. Min Range: -6.8739
Max Act: 6.4676. Min Act: -0.1700
Data Index: 7329118 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8739. Min Range: -6.8739
Max Act: 6.3739. Min Act: -0.1700
Data Index: 5323539 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8739. Min Range: -6.8739
Max Act: 6.3114. Min Act: -0.1700
Data Index: 8022512 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8739. Min Range: -6.8739
Max Act: 6.2801. Min Act: -0.1700
Data Index: 4821150 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8739. Min Range: -6.8739
Max Act: 6.2176. Min Act: -0.1700
Data Index: 5484792 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8739. Min Range: -6.8739
Max Act: 6.1864. Min Act: -0.1700
Data Index: 2868446 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8739. Min Range: -6.8739
Max Act: 6.1864. Min Act: -0.1700
Data Index: 7690925 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8739. Min Range: -6.8739
Max Act: 6.1864. Min Act: -0.1700
Data Index: 4042053 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8739. Min Range: -6.8739
Max Act: 6.1551. Min Act: -0.1700
Data Index: 7228286 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8739. Min Range: -6.8739
Max Act: 6.1551. Min Act: -0.1700
Data Index: 7943154 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8739. Min Range: -6.8739
Max Act: 6.1551. Min Act: -0.1700
Data Index: 3416068 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8739. Min Range: -6.8739
Max Act: 6.1551. Min Act: -0.1700
Data Index: 2360865 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8739. Min Range: -6.8739
Max Act: 6.1239. Min Act: -0.1700
Data Index: 2063503 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8739. Min Range: -6.8739
Max Act: 6.0926. Min Act: -0.1700
Data Index: 182643 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8739. Min Range: -6.8739
Max Act: 6.0926. Min Act: -0.1700
Data Index: 7964660 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8739. Min Range: -6.8739
Max Act: 6.0926. Min Act: -0.1700
Data Index: 335604 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8739. Min Range: -6.8739
Max Act: 6.0926. Min Act: -0.1700
Data Index: 2136032 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8739. Min Range: -6.8739
Max Act: 6.0614. Min Act: -0.1700
Data Index: 37237 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #19