Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2823 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7535. Min Range: -4.7535
Max Act: 4.7535. Min Act: -0.1700
Data Index: 5219301 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7535. Min Range: -4.7535
Max Act: 4.6910. Min Act: -0.1700
Data Index: 7781564 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7535. Min Range: -4.7535
Max Act: 4.6910. Min Act: -0.1700
Data Index: 3808858 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7535. Min Range: -4.7535
Max Act: 4.6910. Min Act: -0.1700
Data Index: 1576836 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7535. Min Range: -4.7535
Max Act: 4.6285. Min Act: -0.1700
Data Index: 4212266 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7535. Min Range: -4.7535
Max Act: 4.6285. Min Act: -0.1700
Data Index: 3015161 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7535. Min Range: -4.7535
Max Act: 4.5973. Min Act: -0.1700
Data Index: 7406066 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7535. Min Range: -4.7535
Max Act: 4.5973. Min Act: -0.1700
Data Index: 6369617 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7535. Min Range: -4.7535
Max Act: 4.5348. Min Act: -0.1700
Data Index: 5484921 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7535. Min Range: -4.7535
Max Act: 4.5660. Min Act: -0.1700
Data Index: 5700390 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7535. Min Range: -4.7535
Max Act: 4.5348. Min Act: -0.1700
Data Index: 4734994 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7535. Min Range: -4.7535
Max Act: 4.5035. Min Act: -0.1700
Data Index: 320792 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7535. Min Range: -4.7535
Max Act: 4.5035. Min Act: -0.1700
Data Index: 6531162 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7535. Min Range: -4.7535
Max Act: 4.5035. Min Act: -0.1700
Data Index: 7178543 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7535. Min Range: -4.7535
Max Act: 4.5035. Min Act: -0.1700
Data Index: 7307846 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7535. Min Range: -4.7535
Max Act: 4.4723. Min Act: -0.1700
Data Index: 5043691 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7535. Min Range: -4.7535
Max Act: 4.4723. Min Act: -0.1700
Data Index: 4278276 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7535. Min Range: -4.7535
Max Act: 4.4410. Min Act: -0.1700
Data Index: 4637011 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7535. Min Range: -4.7535
Max Act: 4.4410. Min Act: -0.1700
Data Index: 1231809 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7535. Min Range: -4.7535
Max Act: 4.4410. Min Act: -0.1700
Data Index: 6979490 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #19