Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5367 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8830. Min Range: -5.8830
Max Act: 5.8517. Min Act: -0.1700
Data Index: 692752 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8830. Min Range: -5.8830
Max Act: 5.8830. Min Act: -0.1700
Data Index: 6762857 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8830. Min Range: -5.8830
Max Act: 5.7580. Min Act: -0.1700
Data Index: 3792531 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8830. Min Range: -5.8830
Max Act: 5.7267. Min Act: -0.1700
Data Index: 3971841 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8830. Min Range: -5.8830
Max Act: 5.7267. Min Act: -0.1700
Data Index: 2262319 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8830. Min Range: -5.8830
Max Act: 5.6642. Min Act: -0.1700
Data Index: 3991232 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8830. Min Range: -5.8830
Max Act: 5.6955. Min Act: -0.1700
Data Index: 4518188 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8830. Min Range: -5.8830
Max Act: 5.6642. Min Act: -0.1700
Data Index: 996303 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8830. Min Range: -5.8830
Max Act: 5.6330. Min Act: -0.1700
Data Index: 6376895 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8830. Min Range: -5.8830
Max Act: 5.5392. Min Act: -0.1700
Data Index: 1063683 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8830. Min Range: -5.8830
Max Act: 5.5392. Min Act: -0.1700
Data Index: 8280158 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8830. Min Range: -5.8830
Max Act: 5.5080. Min Act: -0.1700
Data Index: 2621927 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8830. Min Range: -5.8830
Max Act: 5.5080. Min Act: -0.1700
Data Index: 6787762 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8830. Min Range: -5.8830
Max Act: 5.5080. Min Act: -0.1700
Data Index: 3529774 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8830. Min Range: -5.8830
Max Act: 5.5080. Min Act: -0.1700
Data Index: 3687172 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8830. Min Range: -5.8830
Max Act: 5.4455. Min Act: -0.1700
Data Index: 511016 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8830. Min Range: -5.8830
Max Act: 5.4767. Min Act: -0.1700
Data Index: 7262055 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8830. Min Range: -5.8830
Max Act: 5.4767. Min Act: -0.1700
Data Index: 1474995 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8830. Min Range: -5.8830
Max Act: 5.4767. Min Act: -0.1700
Data Index: 5577958 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8830. Min Range: -5.8830
Max Act: 5.4142. Min Act: -0.1700
Data Index: 6038498 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #19