Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2398 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7536. Min Range: -3.7536
Max Act: 3.7536. Min Act: -0.1700
Data Index: 3350920 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7536. Min Range: -3.7536
Max Act: 3.7067. Min Act: -0.1700
Data Index: 18909 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7536. Min Range: -3.7536
Max Act: 3.6597. Min Act: -0.1700
Data Index: 2360928 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7536. Min Range: -3.7536
Max Act: 3.6597. Min Act: -0.1700
Data Index: 2381454 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7536. Min Range: -3.7536
Max Act: 3.6441. Min Act: -0.1700
Data Index: 876671 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7536. Min Range: -3.7536
Max Act: 3.6441. Min Act: -0.1700
Data Index: 5005473 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7536. Min Range: -3.7536
Max Act: 3.6441. Min Act: -0.1700
Data Index: 7371367 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7536. Min Range: -3.7536
Max Act: 3.6284. Min Act: -0.1700
Data Index: 6330770 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7536. Min Range: -3.7536
Max Act: 3.6284. Min Act: -0.1700
Data Index: 1834114 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7536. Min Range: -3.7536
Max Act: 3.6128. Min Act: -0.1700
Data Index: 2850003 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7536. Min Range: -3.7536
Max Act: 3.5815. Min Act: -0.1700
Data Index: 1797162 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7536. Min Range: -3.7536
Max Act: 3.5815. Min Act: -0.1700
Data Index: 8029534 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7536. Min Range: -3.7536
Max Act: 3.5971. Min Act: -0.1700
Data Index: 6130667 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7536. Min Range: -3.7536
Max Act: 3.5815. Min Act: -0.1700
Data Index: 6361481 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7536. Min Range: -3.7536
Max Act: 3.5815. Min Act: -0.1700
Data Index: 3751312 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7536. Min Range: -3.7536
Max Act: 3.5815. Min Act: -0.1700
Data Index: 432973 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7536. Min Range: -3.7536
Max Act: 3.5658. Min Act: -0.1700
Data Index: 1789274 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7536. Min Range: -3.7536
Max Act: 3.5658. Min Act: -0.1700
Data Index: 5373996 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7536. Min Range: -3.7536
Max Act: 3.5502. Min Act: -0.1700
Data Index: 699595 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7536. Min Range: -3.7536
Max Act: 3.5658. Min Act: -0.1700
Data Index: 6751909 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #19