Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2734 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3071. Min Range: -4.3071
Max Act: 4.3071. Min Act: -0.1700
Data Index: 6662264 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3071. Min Range: -4.3071
Max Act: 4.1509. Min Act: -0.1700
Data Index: 2136657 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3071. Min Range: -4.3071
Max Act: 4.1196. Min Act: -0.1700
Data Index: 2477298 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3071. Min Range: -4.3071
Max Act: 4.1196. Min Act: -0.1700
Data Index: 3449859 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3071. Min Range: -4.3071
Max Act: 4.0571. Min Act: -0.1700
Data Index: 3616460 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3071. Min Range: -4.3071
Max Act: 4.0258. Min Act: -0.1700
Data Index: 2737071 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3071. Min Range: -4.3071
Max Act: 3.9321. Min Act: -0.1700
Data Index: 3523761 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3071. Min Range: -4.3071
Max Act: 3.9633. Min Act: -0.1700
Data Index: 5601165 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3071. Min Range: -4.3071
Max Act: 3.9321. Min Act: -0.1700
Data Index: 3425345 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3071. Min Range: -4.3071
Max Act: 3.9321. Min Act: -0.1700
Data Index: 2034994 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3071. Min Range: -4.3071
Max Act: 3.9008. Min Act: -0.1700
Data Index: 7125639 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3071. Min Range: -4.3071
Max Act: 3.8695. Min Act: -0.1700
Data Index: 3957852 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3071. Min Range: -4.3071
Max Act: 3.9008. Min Act: -0.1700
Data Index: 3032977 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3071. Min Range: -4.3071
Max Act: 3.8695. Min Act: -0.1700
Data Index: 1601723 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3071. Min Range: -4.3071
Max Act: 3.8383. Min Act: -0.1700
Data Index: 682995 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3071. Min Range: -4.3071
Max Act: 3.8070. Min Act: -0.1700
Data Index: 1278687 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3071. Min Range: -4.3071
Max Act: 3.8383. Min Act: -0.1700
Data Index: 6550814 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3071. Min Range: -4.3071
Max Act: 3.8070. Min Act: -0.1700
Data Index: 5469899 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3071. Min Range: -4.3071
Max Act: 3.8070. Min Act: -0.1700
Data Index: 1301174 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3071. Min Range: -4.3071
Max Act: 3.8383. Min Act: -0.1700
Data Index: 3611744 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #19