Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3642 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2807. Min Range: -7.2807
Max Act: 7.2807. Min Act: -0.1700
Data Index: 5957509 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2807. Min Range: -7.2807
Max Act: 6.8432. Min Act: -0.1700
Data Index: 3106793 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2807. Min Range: -7.2807
Max Act: 6.6557. Min Act: -0.1700
Data Index: 6993944 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2807. Min Range: -7.2807
Max Act: 6.6244. Min Act: -0.1700
Data Index: 6006481 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2807. Min Range: -7.2807
Max Act: 6.5932. Min Act: -0.1700
Data Index: 3860720 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2807. Min Range: -7.2807
Max Act: 6.5932. Min Act: -0.1700
Data Index: 7240473 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2807. Min Range: -7.2807
Max Act: 6.5619. Min Act: -0.1700
Data Index: 7836999 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2807. Min Range: -7.2807
Max Act: 6.5619. Min Act: -0.1700
Data Index: 242490 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2807. Min Range: -7.2807
Max Act: 6.5307. Min Act: -0.1700
Data Index: 8581338 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2807. Min Range: -7.2807
Max Act: 6.4994. Min Act: -0.1700
Data Index: 1459309 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2807. Min Range: -7.2807
Max Act: 6.5307. Min Act: -0.1700
Data Index: 6904145 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2807. Min Range: -7.2807
Max Act: 6.4369. Min Act: -0.1700
Data Index: 3708253 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2807. Min Range: -7.2807
Max Act: 6.4369. Min Act: -0.1700
Data Index: 7910251 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2807. Min Range: -7.2807
Max Act: 6.4057. Min Act: -0.1700
Data Index: 3138709 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2807. Min Range: -7.2807
Max Act: 6.3744. Min Act: -0.1700
Data Index: 2252992 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2807. Min Range: -7.2807
Max Act: 6.4057. Min Act: -0.1700
Data Index: 2706268 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2807. Min Range: -7.2807
Max Act: 6.3119. Min Act: -0.1700
Data Index: 6571982 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2807. Min Range: -7.2807
Max Act: 6.3432. Min Act: -0.1700
Data Index: 2296130 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2807. Min Range: -7.2807
Max Act: 6.3432. Min Act: -0.1700
Data Index: 457258 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2807. Min Range: -7.2807
Max Act: 6.3432. Min Act: -0.1700
Data Index: 819162 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19