Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2826 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1736. Min Range: -10.1736
Max Act: 10.1736. Min Act: -0.1700
Data Index: 5844061 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1736. Min Range: -10.1736
Max Act: 10.1111. Min Act: -0.1700
Data Index: 2055953 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1736. Min Range: -10.1736
Max Act: 9.7361. Min Act: -0.1700
Data Index: 5703760 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1736. Min Range: -10.1736
Max Act: 9.6111. Min Act: -0.1700
Data Index: 2525717 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1736. Min Range: -10.1736
Max Act: 9.6111. Min Act: -0.1700
Data Index: 8524795 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1736. Min Range: -10.1736
Max Act: 9.5486. Min Act: -0.1700
Data Index: 807651 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1736. Min Range: -10.1736
Max Act: 9.4861. Min Act: -0.1700
Data Index: 3798730 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1736. Min Range: -10.1736
Max Act: 9.5486. Min Act: -0.1700
Data Index: 6750721 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1736. Min Range: -10.1736
Max Act: 9.4236. Min Act: -0.1700
Data Index: 2014050 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1736. Min Range: -10.1736
Max Act: 9.4236. Min Act: -0.1700
Data Index: 5902214 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1736. Min Range: -10.1736
Max Act: 9.4861. Min Act: -0.1700
Data Index: 6815539 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1736. Min Range: -10.1736
Max Act: 9.4236. Min Act: -0.1700
Data Index: 544107 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1736. Min Range: -10.1736
Max Act: 9.2361. Min Act: -0.1700
Data Index: 3436905 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1736. Min Range: -10.1736
Max Act: 9.2986. Min Act: -0.1700
Data Index: 2011174 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1736. Min Range: -10.1736
Max Act: 9.2986. Min Act: -0.1700
Data Index: 7853754 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1736. Min Range: -10.1736
Max Act: 9.2361. Min Act: -0.1700
Data Index: 7720867 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1736. Min Range: -10.1736
Max Act: 9.2361. Min Act: -0.1700
Data Index: 4533886 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1736. Min Range: -10.1736
Max Act: 9.2361. Min Act: -0.1700
Data Index: 6060453 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1736. Min Range: -10.1736
Max Act: 9.2361. Min Act: -0.1700
Data Index: 755123 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1736. Min Range: -10.1736
Max Act: 9.1736. Min Act: -0.1700
Data Index: 3662786 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #19