Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 922 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7713. Min Range: -5.7713
Max Act: 5.7713. Min Act: -0.1700
Data Index: 1397370 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7713. Min Range: -5.7713
Max Act: 5.7713. Min Act: -0.1699
Data Index: 1397369 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7713. Min Range: -5.7713
Max Act: 5.7713. Min Act: -0.1700
Data Index: 6511826 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7713. Min Range: -5.7713
Max Act: 5.6775. Min Act: -0.1700
Data Index: 334525 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7713. Min Range: -5.7713
Max Act: 5.6463. Min Act: -0.1700
Data Index: 7254217 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7713. Min Range: -5.7713
Max Act: 5.6150. Min Act: -0.1700
Data Index: 8812153 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7713. Min Range: -5.7713
Max Act: 5.5838. Min Act: -0.1700
Data Index: 7592528 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7713. Min Range: -5.7713
Max Act: 5.5525. Min Act: -0.1700
Data Index: 4269109 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7713. Min Range: -5.7713
Max Act: 5.5838. Min Act: -0.1700
Data Index: 4102524 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7713. Min Range: -5.7713
Max Act: 5.5525. Min Act: -0.1700
Data Index: 933282 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7713. Min Range: -5.7713
Max Act: 5.5525. Min Act: -0.1700
Data Index: 5213379 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7713. Min Range: -5.7713
Max Act: 5.5213. Min Act: -0.1700
Data Index: 419205 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7713. Min Range: -5.7713
Max Act: 5.4900. Min Act: -0.1700
Data Index: 3094714 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7713. Min Range: -5.7713
Max Act: 5.5213. Min Act: -0.1700
Data Index: 6472947 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7713. Min Range: -5.7713
Max Act: 5.4900. Min Act: -0.1700
Data Index: 5834045 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7713. Min Range: -5.7713
Max Act: 5.4588. Min Act: -0.1700
Data Index: 1809525 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7713. Min Range: -5.7713
Max Act: 5.4588. Min Act: -0.1700
Data Index: 5166456 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7713. Min Range: -5.7713
Max Act: 5.4588. Min Act: -0.1700
Data Index: 7283138 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7713. Min Range: -5.7713
Max Act: 5.4275. Min Act: -0.1700
Data Index: 5648442 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7713. Min Range: -5.7713
Max Act: 5.4275. Min Act: -0.1700
Data Index: 4388853 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #19