Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1929 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2571. Min Range: -5.2571
Max Act: 5.2571. Min Act: -0.1700
Data Index: 5872467 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2571. Min Range: -5.2571
Max Act: 5.1946. Min Act: -0.1700
Data Index: 7982300 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2571. Min Range: -5.2571
Max Act: 5.1321. Min Act: -0.1700
Data Index: 3406016 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2571. Min Range: -5.2571
Max Act: 5.0696. Min Act: -0.1700
Data Index: 6709913 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2571. Min Range: -5.2571
Max Act: 5.0071. Min Act: -0.1700
Data Index: 104525 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2571. Min Range: -5.2571
Max Act: 4.9759. Min Act: -0.1700
Data Index: 4967837 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2571. Min Range: -5.2571
Max Act: 5.0071. Min Act: -0.1700
Data Index: 7837026 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2571. Min Range: -5.2571
Max Act: 4.9446. Min Act: -0.1700
Data Index: 5483026 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2571. Min Range: -5.2571
Max Act: 4.9446. Min Act: -0.1700
Data Index: 3845893 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2571. Min Range: -5.2571
Max Act: 4.8821. Min Act: -0.1700
Data Index: 6146122 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2571. Min Range: -5.2571
Max Act: 4.8821. Min Act: -0.1700
Data Index: 3692412 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2571. Min Range: -5.2571
Max Act: 4.8821. Min Act: -0.1700
Data Index: 1320083 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2571. Min Range: -5.2571
Max Act: 4.8821. Min Act: -0.1700
Data Index: 3719092 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2571. Min Range: -5.2571
Max Act: 4.8821. Min Act: -0.1700
Data Index: 888105 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2571. Min Range: -5.2571
Max Act: 4.8509. Min Act: -0.1700
Data Index: 4318945 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2571. Min Range: -5.2571
Max Act: 4.8196. Min Act: -0.1700
Data Index: 1978973 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2571. Min Range: -5.2571
Max Act: 4.8196. Min Act: -0.1700
Data Index: 3505724 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2571. Min Range: -5.2571
Max Act: 4.7884. Min Act: -0.1700
Data Index: 7652026 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2571. Min Range: -5.2571
Max Act: 4.8196. Min Act: -0.1700
Data Index: 5859279 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2571. Min Range: -5.2571
Max Act: 4.8196. Min Act: -0.1700
Data Index: 3784842 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #19