Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4818 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.0515. Min Range: -12.0515
Max Act: 12.0515. Min Act: -0.1700
Data Index: 5269771 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.0515. Min Range: -12.0515
Max Act: 11.8015. Min Act: -0.1700
Data Index: 7474670 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.0515. Min Range: -12.0515
Max Act: 11.7390. Min Act: -0.1700
Data Index: 5059236 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.0515. Min Range: -12.0515
Max Act: 11.7390. Min Act: -0.1699
Data Index: 3097052 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.0515. Min Range: -12.0515
Max Act: 11.6140. Min Act: -0.1700
Data Index: 5308481 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.0515. Min Range: -12.0515
Max Act: 11.6140. Min Act: -0.1700
Data Index: 6050974 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.0515. Min Range: -12.0515
Max Act: 11.5515. Min Act: -0.1700
Data Index: 7582033 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.0515. Min Range: -12.0515
Max Act: 11.4890. Min Act: -0.1700
Data Index: 1024673 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.0515. Min Range: -12.0515
Max Act: 11.4890. Min Act: -0.1700
Data Index: 708263 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.0515. Min Range: -12.0515
Max Act: 11.4890. Min Act: -0.1700
Data Index: 8239667 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.0515. Min Range: -12.0515
Max Act: 11.4890. Min Act: -0.1700
Data Index: 350139 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.0515. Min Range: -12.0515
Max Act: 11.4265. Min Act: -0.1700
Data Index: 2340121 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.0515. Min Range: -12.0515
Max Act: 11.4265. Min Act: -0.1700
Data Index: 4062869 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.0515. Min Range: -12.0515
Max Act: 11.4265. Min Act: -0.1700
Data Index: 6588188 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.0515. Min Range: -12.0515
Max Act: 11.4265. Min Act: -0.1700
Data Index: 409041 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.0515. Min Range: -12.0515
Max Act: 11.4265. Min Act: -0.1700
Data Index: 6031356 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.0515. Min Range: -12.0515
Max Act: 11.3640. Min Act: -0.1700
Data Index: 1620777 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.0515. Min Range: -12.0515
Max Act: 11.3640. Min Act: -0.1700
Data Index: 2202599 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.0515. Min Range: -12.0515
Max Act: 11.3640. Min Act: -0.1700
Data Index: 1098884 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.0515. Min Range: -12.0515
Max Act: 11.2390. Min Act: -0.1700
Data Index: 2248718 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #19