Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5593 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2937. Min Range: -6.2937
Max Act: 6.2937. Min Act: -0.1700
Data Index: 1022780 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2937. Min Range: -6.2937
Max Act: 5.9812. Min Act: -0.1700
Data Index: 6156496 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2937. Min Range: -6.2937
Max Act: 5.9812. Min Act: -0.1700
Data Index: 49143 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2937. Min Range: -6.2937
Max Act: 5.9812. Min Act: -0.1700
Data Index: 49142 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2937. Min Range: -6.2937
Max Act: 5.9187. Min Act: -0.1700
Data Index: 3479697 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2937. Min Range: -6.2937
Max Act: 5.8874. Min Act: -0.1700
Data Index: 1019327 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2937. Min Range: -6.2937
Max Act: 5.7937. Min Act: -0.1700
Data Index: 1400439 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2937. Min Range: -6.2937
Max Act: 5.7624. Min Act: -0.1700
Data Index: 3289947 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2937. Min Range: -6.2937
Max Act: 5.7312. Min Act: -0.1700
Data Index: 1753995 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2937. Min Range: -6.2937
Max Act: 5.6999. Min Act: -0.1700
Data Index: 2635871 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2937. Min Range: -6.2937
Max Act: 5.6999. Min Act: -0.1700
Data Index: 672801 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2937. Min Range: -6.2937
Max Act: 5.6687. Min Act: -0.1700
Data Index: 5423142 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2937. Min Range: -6.2937
Max Act: 5.6687. Min Act: -0.1700
Data Index: 8699099 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2937. Min Range: -6.2937
Max Act: 5.6374. Min Act: -0.1700
Data Index: 1972372 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2937. Min Range: -6.2937
Max Act: 5.6374. Min Act: -0.1700
Data Index: 1019326 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2937. Min Range: -6.2937
Max Act: 5.6062. Min Act: -0.1700
Data Index: 7316708 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2937. Min Range: -6.2937
Max Act: 5.6062. Min Act: -0.1700
Data Index: 516828 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2937. Min Range: -6.2937
Max Act: 5.5749. Min Act: -0.1700
Data Index: 49137 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2937. Min Range: -6.2937
Max Act: 5.6062. Min Act: -0.1700
Data Index: 7764707 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2937. Min Range: -6.2937
Max Act: 5.5437. Min Act: -0.1700
Data Index: 2648976 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #19