Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4434 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1569. Min Range: -5.1569
Max Act: 5.1569. Min Act: -0.1700
Data Index: 161587 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1569. Min Range: -5.1569
Max Act: 5.1256. Min Act: -0.1700
Data Index: 5791391 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1569. Min Range: -5.1569
Max Act: 5.1256. Min Act: -0.1700
Data Index: 3910634 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1569. Min Range: -5.1569
Max Act: 5.0319. Min Act: -0.1700
Data Index: 1336765 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1569. Min Range: -5.1569
Max Act: 5.0319. Min Act: -0.1700
Data Index: 5131848 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1569. Min Range: -5.1569
Max Act: 5.0319. Min Act: -0.1700
Data Index: 6367411 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1569. Min Range: -5.1569
Max Act: 5.0006. Min Act: -0.1700
Data Index: 4845004 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1569. Min Range: -5.1569
Max Act: 5.0006. Min Act: -0.1700
Data Index: 2657071 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1569. Min Range: -5.1569
Max Act: 5.0319. Min Act: -0.1700
Data Index: 5427834 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1569. Min Range: -5.1569
Max Act: 5.0319. Min Act: -0.1700
Data Index: 2716631 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1569. Min Range: -5.1569
Max Act: 5.0006. Min Act: -0.1700
Data Index: 5927991 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1569. Min Range: -5.1569
Max Act: 4.9694. Min Act: -0.1700
Data Index: 6136869 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1569. Min Range: -5.1569
Max Act: 4.9694. Min Act: -0.1700
Data Index: 4362761 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1569. Min Range: -5.1569
Max Act: 5.0006. Min Act: -0.1700
Data Index: 4558030 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1569. Min Range: -5.1569
Max Act: 5.0006. Min Act: -0.1700
Data Index: 5021410 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1569. Min Range: -5.1569
Max Act: 4.9381. Min Act: -0.1700
Data Index: 4886250 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1569. Min Range: -5.1569
Max Act: 4.9069. Min Act: -0.1700
Data Index: 991863 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1569. Min Range: -5.1569
Max Act: 4.9381. Min Act: -0.1700
Data Index: 1371387 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1569. Min Range: -5.1569
Max Act: 4.9381. Min Act: -0.1700
Data Index: 415259 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1569. Min Range: -5.1569
Max Act: 4.9381. Min Act: -0.1700
Data Index: 1378608 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #19