Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5278 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5057. Min Range: -7.5057
Max Act: 7.5057. Min Act: -0.1700
Data Index: 5387653 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5057. Min Range: -7.5057
Max Act: 7.4744. Min Act: -0.1700
Data Index: 62215 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5057. Min Range: -7.5057
Max Act: 7.3807. Min Act: -0.1700
Data Index: 2674432 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5057. Min Range: -7.5057
Max Act: 7.2557. Min Act: -0.1700
Data Index: 3122126 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5057. Min Range: -7.5057
Max Act: 7.1932. Min Act: -0.1700
Data Index: 2100569 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5057. Min Range: -7.5057
Max Act: 7.1619. Min Act: -0.1700
Data Index: 5371449 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5057. Min Range: -7.5057
Max Act: 7.1307. Min Act: -0.1700
Data Index: 4193168 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5057. Min Range: -7.5057
Max Act: 7.0994. Min Act: -0.1700
Data Index: 6189771 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5057. Min Range: -7.5057
Max Act: 7.0369. Min Act: -0.1700
Data Index: 5736557 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5057. Min Range: -7.5057
Max Act: 6.9744. Min Act: -0.1700
Data Index: 6541580 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5057. Min Range: -7.5057
Max Act: 6.9432. Min Act: -0.1700
Data Index: 5700318 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5057. Min Range: -7.5057
Max Act: 6.9432. Min Act: -0.1700
Data Index: 8222812 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5057. Min Range: -7.5057
Max Act: 6.8807. Min Act: -0.1700
Data Index: 2278617 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5057. Min Range: -7.5057
Max Act: 6.8494. Min Act: -0.1700
Data Index: 5327040 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5057. Min Range: -7.5057
Max Act: 6.8182. Min Act: -0.1700
Data Index: 1836875 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5057. Min Range: -7.5057
Max Act: 6.8182. Min Act: -0.1700
Data Index: 1706661 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5057. Min Range: -7.5057
Max Act: 6.7869. Min Act: -0.1700
Data Index: 5369274 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5057. Min Range: -7.5057
Max Act: 6.7557. Min Act: -0.1700
Data Index: 2580295 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5057. Min Range: -7.5057
Max Act: 6.7557. Min Act: -0.1700
Data Index: 6033340 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5057. Min Range: -7.5057
Max Act: 6.7557. Min Act: -0.1700
Data Index: 336923 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #19