Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2772 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9285. Min Range: -6.9285
Max Act: 6.9285. Min Act: -0.1700
Data Index: 3276697 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9285. Min Range: -6.9285
Max Act: 6.5535. Min Act: -0.1700
Data Index: 8827246 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9285. Min Range: -6.9285
Max Act: 6.5222. Min Act: -0.1700
Data Index: 1222254 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9285. Min Range: -6.9285
Max Act: 6.4910. Min Act: -0.1700
Data Index: 3042627 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9285. Min Range: -6.9285
Max Act: 6.4285. Min Act: -0.1700
Data Index: 3582927 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9285. Min Range: -6.9285
Max Act: 6.3972. Min Act: -0.1700
Data Index: 6178357 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9285. Min Range: -6.9285
Max Act: 6.3972. Min Act: -0.1700
Data Index: 1193029 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9285. Min Range: -6.9285
Max Act: 6.3972. Min Act: -0.1700
Data Index: 269572 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9285. Min Range: -6.9285
Max Act: 6.3972. Min Act: -0.1700
Data Index: 8546292 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9285. Min Range: -6.9285
Max Act: 6.3660. Min Act: -0.1700
Data Index: 2472674 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9285. Min Range: -6.9285
Max Act: 6.3660. Min Act: -0.1700
Data Index: 6930816 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9285. Min Range: -6.9285
Max Act: 6.3972. Min Act: -0.1700
Data Index: 7285689 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9285. Min Range: -6.9285
Max Act: 6.3660. Min Act: -0.1700
Data Index: 7454438 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9285. Min Range: -6.9285
Max Act: 6.3347. Min Act: -0.1700
Data Index: 8583424 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9285. Min Range: -6.9285
Max Act: 6.3347. Min Act: -0.1700
Data Index: 6178358 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9285. Min Range: -6.9285
Max Act: 6.3035. Min Act: -0.1700
Data Index: 2672826 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9285. Min Range: -6.9285
Max Act: 6.2722. Min Act: -0.1700
Data Index: 3185736 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9285. Min Range: -6.9285
Max Act: 6.2722. Min Act: -0.1700
Data Index: 1185515 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9285. Min Range: -6.9285
Max Act: 6.2722. Min Act: -0.1700
Data Index: 6768090 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9285. Min Range: -6.9285
Max Act: 6.3035. Min Act: -0.1700
Data Index: 6790118 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #19