Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4938 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6961. Min Range: -6.6961
Max Act: 6.6961. Min Act: -0.1700
Data Index: 3715960 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6961. Min Range: -6.6961
Max Act: 6.5398. Min Act: -0.1700
Data Index: 2967178 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6961. Min Range: -6.6961
Max Act: 6.3211. Min Act: -0.1700
Data Index: 8470302 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6961. Min Range: -6.6961
Max Act: 6.2586. Min Act: -0.1700
Data Index: 2026554 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6961. Min Range: -6.6961
Max Act: 6.1648. Min Act: -0.1700
Data Index: 1692879 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6961. Min Range: -6.6961
Max Act: 6.1023. Min Act: -0.1700
Data Index: 7918812 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6961. Min Range: -6.6961
Max Act: 6.0711. Min Act: -0.1700
Data Index: 4145634 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6961. Min Range: -6.6961
Max Act: 6.1023. Min Act: -0.1700
Data Index: 7864553 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6961. Min Range: -6.6961
Max Act: 6.0711. Min Act: -0.1700
Data Index: 8571966 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6961. Min Range: -6.6961
Max Act: 6.0711. Min Act: -0.1700
Data Index: 4413621 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6961. Min Range: -6.6961
Max Act: 6.0086. Min Act: -0.1700
Data Index: 3664952 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6961. Min Range: -6.6961
Max Act: 6.0086. Min Act: -0.1700
Data Index: 8712934 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6961. Min Range: -6.6961
Max Act: 6.0711. Min Act: -0.1700
Data Index: 1570790 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6961. Min Range: -6.6961
Max Act: 6.0086. Min Act: -0.1700
Data Index: 7806993 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6961. Min Range: -6.6961
Max Act: 6.0086. Min Act: -0.1700
Data Index: 5382393 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6961. Min Range: -6.6961
Max Act: 6.0086. Min Act: -0.1700
Data Index: 4126263 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6961. Min Range: -6.6961
Max Act: 6.0086. Min Act: -0.1700
Data Index: 5346247 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6961. Min Range: -6.6961
Max Act: 5.9773. Min Act: -0.1700
Data Index: 4673276 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6961. Min Range: -6.6961
Max Act: 5.9773. Min Act: -0.1700
Data Index: 3449595 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6961. Min Range: -6.6961
Max Act: 5.9773. Min Act: -0.1700
Data Index: 4049028 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #19