Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3704 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7185. Min Range: -7.7185
Max Act: 7.7185. Min Act: -0.1700
Data Index: 4283137 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7185. Min Range: -7.7185
Max Act: 7.6248. Min Act: -0.1700
Data Index: 6744304 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7185. Min Range: -7.7185
Max Act: 7.6248. Min Act: -0.1700
Data Index: 5213378 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7185. Min Range: -7.7185
Max Act: 7.4998. Min Act: -0.1700
Data Index: 5272258 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7185. Min Range: -7.7185
Max Act: 7.4998. Min Act: -0.1700
Data Index: 5542539 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7185. Min Range: -7.7185
Max Act: 7.4373. Min Act: -0.1700
Data Index: 1769689 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7185. Min Range: -7.7185
Max Act: 7.4373. Min Act: -0.1700
Data Index: 5213389 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7185. Min Range: -7.7185
Max Act: 7.2498. Min Act: -0.1700
Data Index: 8384423 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7185. Min Range: -7.7185
Max Act: 7.1873. Min Act: -0.1700
Data Index: 3237361 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7185. Min Range: -7.7185
Max Act: 7.1873. Min Act: -0.1700
Data Index: 4422440 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7185. Min Range: -7.7185
Max Act: 7.1873. Min Act: -0.1700
Data Index: 4269974 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7185. Min Range: -7.7185
Max Act: 7.1560. Min Act: -0.1700
Data Index: 1892260 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7185. Min Range: -7.7185
Max Act: 7.1248. Min Act: -0.1700
Data Index: 907562 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7185. Min Range: -7.7185
Max Act: 7.1248. Min Act: -0.1700
Data Index: 6301920 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7185. Min Range: -7.7185
Max Act: 7.1248. Min Act: -0.1700
Data Index: 571518 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7185. Min Range: -7.7185
Max Act: 7.0623. Min Act: -0.1700
Data Index: 3125891 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7185. Min Range: -7.7185
Max Act: 7.0310. Min Act: -0.1700
Data Index: 1195930 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7185. Min Range: -7.7185
Max Act: 6.9998. Min Act: -0.1700
Data Index: 5432214 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7185. Min Range: -7.7185
Max Act: 6.9685. Min Act: -0.1700
Data Index: 3604825 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7185. Min Range: -7.7185
Max Act: 6.9373. Min Act: -0.1700
Data Index: 4243077 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #19