Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4654 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2194. Min Range: -5.2194
Max Act: 5.2194. Min Act: -0.1700
Data Index: 5078761 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2194. Min Range: -5.2194
Max Act: 5.1569. Min Act: -0.1700
Data Index: 7807357 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2194. Min Range: -5.2194
Max Act: 5.1569. Min Act: -0.1700
Data Index: 1127024 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2194. Min Range: -5.2194
Max Act: 5.1256. Min Act: -0.1692
Data Index: 5325594 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2194. Min Range: -5.2194
Max Act: 5.0944. Min Act: -0.1700
Data Index: 5853436 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2194. Min Range: -5.2194
Max Act: 5.0944. Min Act: -0.1700
Data Index: 8508872 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2194. Min Range: -5.2194
Max Act: 5.0631. Min Act: -0.1700
Data Index: 8686272 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2194. Min Range: -5.2194
Max Act: 5.0944. Min Act: -0.1700
Data Index: 5739727 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2194. Min Range: -5.2194
Max Act: 5.0319. Min Act: -0.1700
Data Index: 4288914 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2194. Min Range: -5.2194
Max Act: 5.0006. Min Act: -0.1700
Data Index: 5184206 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2194. Min Range: -5.2194
Max Act: 5.0319. Min Act: -0.1700
Data Index: 2951381 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2194. Min Range: -5.2194
Max Act: 5.0006. Min Act: -0.1700
Data Index: 7353273 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2194. Min Range: -5.2194
Max Act: 5.0006. Min Act: -0.1700
Data Index: 8265899 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2194. Min Range: -5.2194
Max Act: 5.0006. Min Act: -0.1700
Data Index: 2187990 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2194. Min Range: -5.2194
Max Act: 5.0006. Min Act: -0.1700
Data Index: 2480381 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2194. Min Range: -5.2194
Max Act: 5.0006. Min Act: -0.1700
Data Index: 6051574 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2194. Min Range: -5.2194
Max Act: 5.0006. Min Act: -0.1699
Data Index: 2643934 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2194. Min Range: -5.2194
Max Act: 4.9694. Min Act: -0.1700
Data Index: 2078967 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2194. Min Range: -5.2194
Max Act: 5.0006. Min Act: -0.1700
Data Index: 5975910 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2194. Min Range: -5.2194
Max Act: 4.9694. Min Act: -0.1700
Data Index: 769609 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #19