Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3044 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4807. Min Range: -7.4807
Max Act: 7.4807. Min Act: -0.1700
Data Index: 6569922 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4807. Min Range: -7.4807
Max Act: 7.3557. Min Act: -0.1700
Data Index: 3768299 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4807. Min Range: -7.4807
Max Act: 7.3557. Min Act: -0.1700
Data Index: 2964459 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4807. Min Range: -7.4807
Max Act: 7.3557. Min Act: -0.1700
Data Index: 4254535 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4807. Min Range: -7.4807
Max Act: 7.2619. Min Act: -0.1700
Data Index: 6652433 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4807. Min Range: -7.4807
Max Act: 7.1994. Min Act: -0.1700
Data Index: 6842043 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4807. Min Range: -7.4807
Max Act: 7.1057. Min Act: -0.1700
Data Index: 6057063 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4807. Min Range: -7.4807
Max Act: 7.1057. Min Act: -0.1700
Data Index: 4855602 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4807. Min Range: -7.4807
Max Act: 7.1057. Min Act: -0.1700
Data Index: 1113620 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4807. Min Range: -7.4807
Max Act: 7.0744. Min Act: -0.1700
Data Index: 6392854 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4807. Min Range: -7.4807
Max Act: 7.0744. Min Act: -0.1700
Data Index: 413530 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4807. Min Range: -7.4807
Max Act: 7.0432. Min Act: -0.1700
Data Index: 3393886 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4807. Min Range: -7.4807
Max Act: 7.0432. Min Act: -0.1700
Data Index: 4700467 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4807. Min Range: -7.4807
Max Act: 7.0119. Min Act: -0.1700
Data Index: 2888152 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4807. Min Range: -7.4807
Max Act: 6.9494. Min Act: -0.1700
Data Index: 6955607 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4807. Min Range: -7.4807
Max Act: 6.9494. Min Act: -0.1700
Data Index: 7433650 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4807. Min Range: -7.4807
Max Act: 6.9494. Min Act: -0.1700
Data Index: 675411 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4807. Min Range: -7.4807
Max Act: 6.9494. Min Act: -0.1700
Data Index: 4744568 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4807. Min Range: -7.4807
Max Act: 6.9494. Min Act: -0.1700
Data Index: 4462207 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4807. Min Range: -7.4807
Max Act: 6.9182. Min Act: -0.1700
Data Index: 5133695 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #19