Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1813 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.3092. Min Range: -2.3092
Max Act: 2.3092. Min Act: -0.1700
Data Index: 6157415 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3092. Min Range: -2.3092
Max Act: 2.2598. Min Act: -0.1700
Data Index: 7239141 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3092. Min Range: -2.3092
Max Act: 2.1936. Min Act: -0.1700
Data Index: 8489975 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3092. Min Range: -2.3092
Max Act: 2.1436. Min Act: -0.1700
Data Index: 4187332 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3092. Min Range: -2.3092
Max Act: 2.0935. Min Act: -0.1700
Data Index: 2943221 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3092. Min Range: -2.3092
Max Act: 2.0431. Min Act: -0.1700
Data Index: 465745 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3092. Min Range: -2.3092
Max Act: 2.0431. Min Act: -0.1700
Data Index: 8424375 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3092. Min Range: -2.3092
Max Act: 2.0263. Min Act: -0.1700
Data Index: 194646 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3092. Min Range: -2.3092
Max Act: 2.0094. Min Act: -0.1700
Data Index: 7494224 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3092. Min Range: -2.3092
Max Act: 2.0094. Min Act: -0.1699
Data Index: 5142665 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3092. Min Range: -2.3092
Max Act: 1.9925. Min Act: -0.1700
Data Index: 6591239 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3092. Min Range: -2.3092
Max Act: 1.9925. Min Act: -0.1700
Data Index: 8497672 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3092. Min Range: -2.3092
Max Act: 1.9925. Min Act: -0.1700
Data Index: 2362804 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3092. Min Range: -2.3092
Max Act: 1.9756. Min Act: -0.1700
Data Index: 3203223 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3092. Min Range: -2.3092
Max Act: 1.9246. Min Act: -0.1700
Data Index: 6312039 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3092. Min Range: -2.3092
Max Act: 1.9076. Min Act: -0.1700
Data Index: 5700010 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3092. Min Range: -2.3092
Max Act: 1.9246. Min Act: -0.1700
Data Index: 7370947 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3092. Min Range: -2.3092
Max Act: 1.9076. Min Act: -0.1695
Data Index: 5601470 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3092. Min Range: -2.3092
Max Act: 1.9076. Min Act: -0.1698
Data Index: 4754885 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3092. Min Range: -2.3092
Max Act: 1.8735. Min Act: -0.1699
Data Index: 4224656 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #19