Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3213 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4265. Min Range: -9.4265
Max Act: 9.4265. Min Act: -0.1700
Data Index: 4937124 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4265. Min Range: -9.4265
Max Act: 9.3640. Min Act: -0.1700
Data Index: 2005303 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4265. Min Range: -9.4265
Max Act: 9.3015. Min Act: -0.1665
Data Index: 1755555 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4265. Min Range: -9.4265
Max Act: 9.2390. Min Act: -0.1692
Data Index: 113681 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4265. Min Range: -9.4265
Max Act: 9.3015. Min Act: -0.1700
Data Index: 3094108 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4265. Min Range: -9.4265
Max Act: 9.1140. Min Act: -0.1700
Data Index: 2686346 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4265. Min Range: -9.4265
Max Act: 9.1140. Min Act: -0.1700
Data Index: 8767673 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4265. Min Range: -9.4265
Max Act: 8.9890. Min Act: -0.1700
Data Index: 359861 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4265. Min Range: -9.4265
Max Act: 8.9890. Min Act: -0.1700
Data Index: 4472496 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4265. Min Range: -9.4265
Max Act: 9.0515. Min Act: -0.1700
Data Index: 365148 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4265. Min Range: -9.4265
Max Act: 8.9265. Min Act: -0.1700
Data Index: 423437 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4265. Min Range: -9.4265
Max Act: 8.9265. Min Act: -0.1700
Data Index: 2370930 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4265. Min Range: -9.4265
Max Act: 8.8640. Min Act: -0.1700
Data Index: 8742193 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4265. Min Range: -9.4265
Max Act: 8.8640. Min Act: -0.1700
Data Index: 4082953 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4265. Min Range: -9.4265
Max Act: 8.8640. Min Act: -0.1700
Data Index: 1925382 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4265. Min Range: -9.4265
Max Act: 8.8640. Min Act: -0.1700
Data Index: 656147 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4265. Min Range: -9.4265
Max Act: 8.8640. Min Act: -0.1700
Data Index: 7674121 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4265. Min Range: -9.4265
Max Act: 8.7390. Min Act: -0.1700
Data Index: 5974927 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4265. Min Range: -9.4265
Max Act: 8.8015. Min Act: -0.1700
Data Index: 7304166 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4265. Min Range: -9.4265
Max Act: 8.8015. Min Act: -0.1700
Data Index: 1848783 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #19