Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2917 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7576. Min Range: -1.7576
Max Act: 1.7576. Min Act: -0.1699
Data Index: 6251009 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7576. Min Range: -1.7576
Max Act: 1.7576. Min Act: -0.1700
Data Index: 7060918 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7576. Min Range: -1.7576
Max Act: 1.7230. Min Act: -0.1700
Data Index: 8484767 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7576. Min Range: -1.7576
Max Act: 1.7230. Min Act: -0.1699
Data Index: 770281 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7576. Min Range: -1.7576
Max Act: 1.7403. Min Act: -0.1700
Data Index: 8530096 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7576. Min Range: -1.7576
Max Act: 1.7143. Min Act: -0.1700
Data Index: 3744472 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7576. Min Range: -1.7576
Max Act: 1.7230. Min Act: -0.1700
Data Index: 5590307 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7576. Min Range: -1.7576
Max Act: 1.7230. Min Act: -0.1700
Data Index: 8166941 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7576. Min Range: -1.7576
Max Act: 1.7057. Min Act: -0.1700
Data Index: 3303372 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7576. Min Range: -1.7576
Max Act: 1.7057. Min Act: -0.1700
Data Index: 3395327 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7576. Min Range: -1.7576
Max Act: 1.6970. Min Act: -0.1700
Data Index: 5986569 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7576. Min Range: -1.7576
Max Act: 1.6883. Min Act: -0.1700
Data Index: 5561931 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7576. Min Range: -1.7576
Max Act: 1.6883. Min Act: -0.1700
Data Index: 3943303 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7576. Min Range: -1.7576
Max Act: 1.6623. Min Act: -0.1700
Data Index: 848696 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7576. Min Range: -1.7576
Max Act: 1.6797. Min Act: -0.1700
Data Index: 159265 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7576. Min Range: -1.7576
Max Act: 1.6623. Min Act: -0.1700
Data Index: 4148660 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7576. Min Range: -1.7576
Max Act: 1.6623. Min Act: -0.1700
Data Index: 5790127 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7576. Min Range: -1.7576
Max Act: 1.6536. Min Act: -0.1700
Data Index: 4933874 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7576. Min Range: -1.7576
Max Act: 1.6623. Min Act: -0.1700
Data Index: 8709255 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7576. Min Range: -1.7576
Max Act: 1.6797. Min Act: -0.1700
Data Index: 4463380 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #19