Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2479 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1980. Min Range: -4.1980
Max Act: 4.1980. Min Act: -0.1700
Data Index: 734571 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1980. Min Range: -4.1980
Max Act: 4.1042. Min Act: -0.1700
Data Index: 876322 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1980. Min Range: -4.1980
Max Act: 4.0729. Min Act: -0.1700
Data Index: 939101 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1980. Min Range: -4.1980
Max Act: 4.0417. Min Act: -0.1700
Data Index: 7385540 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1980. Min Range: -4.1980
Max Act: 4.0104. Min Act: -0.1700
Data Index: 1128722 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1980. Min Range: -4.1980
Max Act: 3.9479. Min Act: -0.1700
Data Index: 5369019 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1980. Min Range: -4.1980
Max Act: 3.9792. Min Act: -0.1700
Data Index: 1368941 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1980. Min Range: -4.1980
Max Act: 3.9479. Min Act: -0.1700
Data Index: 4072451 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1980. Min Range: -4.1980
Max Act: 3.9479. Min Act: -0.1700
Data Index: 5887237 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1980. Min Range: -4.1980
Max Act: 3.9166. Min Act: -0.1700
Data Index: 6955336 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1980. Min Range: -4.1980
Max Act: 3.9166. Min Act: -0.1700
Data Index: 8400754 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1980. Min Range: -4.1980
Max Act: 3.8854. Min Act: -0.1700
Data Index: 8188906 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1980. Min Range: -4.1980
Max Act: 3.8854. Min Act: -0.1700
Data Index: 4257115 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1980. Min Range: -4.1980
Max Act: 3.8541. Min Act: -0.1700
Data Index: 1733219 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1980. Min Range: -4.1980
Max Act: 3.8541. Min Act: -0.1700
Data Index: 204007 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1980. Min Range: -4.1980
Max Act: 3.8541. Min Act: -0.1700
Data Index: 6549983 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1980. Min Range: -4.1980
Max Act: 3.8541. Min Act: -0.1700
Data Index: 2278865 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1980. Min Range: -4.1980
Max Act: 3.8541. Min Act: -0.1700
Data Index: 5218721 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1980. Min Range: -4.1980
Max Act: 3.8541. Min Act: -0.1700
Data Index: 179216 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1980. Min Range: -4.1980
Max Act: 3.8541. Min Act: -0.1700
Data Index: 5506187 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #19