Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5980 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3798. Min Range: -5.3798
Max Act: 5.3798. Min Act: -0.1700
Data Index: 313392 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3798. Min Range: -5.3798
Max Act: 5.3798. Min Act: -0.1700
Data Index: 796661 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3798. Min Range: -5.3798
Max Act: 5.3485. Min Act: -0.1700
Data Index: 1680976 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3798. Min Range: -5.3798
Max Act: 5.3173. Min Act: -0.1700
Data Index: 699166 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3798. Min Range: -5.3798
Max Act: 5.2860. Min Act: -0.1700
Data Index: 5738753 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3798. Min Range: -5.3798
Max Act: 5.2548. Min Act: -0.1700
Data Index: 1661706 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3798. Min Range: -5.3798
Max Act: 5.1923. Min Act: -0.1700
Data Index: 151887 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3798. Min Range: -5.3798
Max Act: 5.1923. Min Act: -0.1700
Data Index: 6139965 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3798. Min Range: -5.3798
Max Act: 5.1610. Min Act: -0.1700
Data Index: 8124405 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3798. Min Range: -5.3798
Max Act: 5.1610. Min Act: -0.1700
Data Index: 3803148 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3798. Min Range: -5.3798
Max Act: 5.1610. Min Act: -0.1700
Data Index: 7983435 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3798. Min Range: -5.3798
Max Act: 5.1610. Min Act: -0.1700
Data Index: 3116316 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3798. Min Range: -5.3798
Max Act: 5.1298. Min Act: -0.1700
Data Index: 2100027 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3798. Min Range: -5.3798
Max Act: 5.1298. Min Act: -0.1700
Data Index: 8369177 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3798. Min Range: -5.3798
Max Act: 5.1298. Min Act: -0.1700
Data Index: 4377690 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3798. Min Range: -5.3798
Max Act: 5.0985. Min Act: -0.1700
Data Index: 2813657 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3798. Min Range: -5.3798
Max Act: 5.0673. Min Act: -0.1700
Data Index: 2346178 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3798. Min Range: -5.3798
Max Act: 5.0673. Min Act: -0.1700
Data Index: 5078177 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3798. Min Range: -5.3798
Max Act: 5.0673. Min Act: -0.1700
Data Index: 6692451 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3798. Min Range: -5.3798
Max Act: 5.0673. Min Act: -0.1700
Data Index: 7829982 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #19