Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1586 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6693. Min Range: -4.6693
Max Act: 4.6693. Min Act: -0.1700
Data Index: 7134449 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6693. Min Range: -4.6693
Max Act: 4.4506. Min Act: -0.1700
Data Index: 3743952 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6693. Min Range: -4.6693
Max Act: 4.4506. Min Act: -0.1700
Data Index: 6150563 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6693. Min Range: -4.6693
Max Act: 4.4193. Min Act: -0.1700
Data Index: 3743944 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6693. Min Range: -4.6693
Max Act: 4.3256. Min Act: -0.1700
Data Index: 6770926 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6693. Min Range: -4.6693
Max Act: 4.2006. Min Act: -0.1700
Data Index: 5755920 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6693. Min Range: -4.6693
Max Act: 4.2318. Min Act: -0.1700
Data Index: 8214391 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6693. Min Range: -4.6693
Max Act: 4.1381. Min Act: -0.1700
Data Index: 2967634 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6693. Min Range: -4.6693
Max Act: 4.1068. Min Act: -0.1700
Data Index: 4218750 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6693. Min Range: -4.6693
Max Act: 4.1068. Min Act: -0.1700
Data Index: 5908975 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6693. Min Range: -4.6693
Max Act: 4.1068. Min Act: -0.1700
Data Index: 5710014 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6693. Min Range: -4.6693
Max Act: 4.0755. Min Act: -0.1700
Data Index: 6403004 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6693. Min Range: -4.6693
Max Act: 4.0755. Min Act: -0.1700
Data Index: 3662861 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6693. Min Range: -4.6693
Max Act: 4.0130. Min Act: -0.1700
Data Index: 199615 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6693. Min Range: -4.6693
Max Act: 4.0130. Min Act: -0.1700
Data Index: 5013344 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6693. Min Range: -4.6693
Max Act: 4.0130. Min Act: -0.1700
Data Index: 5242444 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6693. Min Range: -4.6693
Max Act: 4.0130. Min Act: -0.1700
Data Index: 7385271 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6693. Min Range: -4.6693
Max Act: 4.0443. Min Act: -0.1700
Data Index: 685666 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6693. Min Range: -4.6693
Max Act: 4.0130. Min Act: -0.1700
Data Index: 685665 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6693. Min Range: -4.6693
Max Act: 4.0130. Min Act: -0.1700
Data Index: 2879001 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #19