Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2816 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2666. Min Range: -3.2666
Max Act: 3.2666. Min Act: -0.1700
Data Index: 2697856 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2666. Min Range: -3.2666
Max Act: 3.2195. Min Act: -0.1700
Data Index: 632922 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2666. Min Range: -3.2666
Max Act: 3.2038. Min Act: -0.1700
Data Index: 2119689 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2666. Min Range: -3.2666
Max Act: 3.1880. Min Act: -0.1700
Data Index: 736448 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2666. Min Range: -3.2666
Max Act: 3.1880. Min Act: -0.1700
Data Index: 4426008 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2666. Min Range: -3.2666
Max Act: 3.1880. Min Act: -0.1700
Data Index: 986686 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2666. Min Range: -3.2666
Max Act: 3.1880. Min Act: -0.1700
Data Index: 5758413 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2666. Min Range: -3.2666
Max Act: 3.1723. Min Act: -0.1700
Data Index: 8310177 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2666. Min Range: -3.2666
Max Act: 3.1723. Min Act: -0.1700
Data Index: 5684147 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2666. Min Range: -3.2666
Max Act: 3.1566. Min Act: -0.1700
Data Index: 8251994 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2666. Min Range: -3.2666
Max Act: 3.1408. Min Act: -0.1700
Data Index: 6299863 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2666. Min Range: -3.2666
Max Act: 3.1566. Min Act: -0.1700
Data Index: 775550 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2666. Min Range: -3.2666
Max Act: 3.1566. Min Act: -0.1700
Data Index: 8449518 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2666. Min Range: -3.2666
Max Act: 3.1408. Min Act: -0.1700
Data Index: 3645414 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2666. Min Range: -3.2666
Max Act: 3.1408. Min Act: -0.1700
Data Index: 3566013 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2666. Min Range: -3.2666
Max Act: 3.1408. Min Act: -0.1700
Data Index: 1804707 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2666. Min Range: -3.2666
Max Act: 3.1408. Min Act: -0.1700
Data Index: 3516150 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2666. Min Range: -3.2666
Max Act: 3.1408. Min Act: -0.1700
Data Index: 5684149 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2666. Min Range: -3.2666
Max Act: 3.1408. Min Act: -0.1700
Data Index: 3454191 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2666. Min Range: -3.2666
Max Act: 3.1566. Min Act: -0.1700
Data Index: 7377950 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19