Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2645 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5017. Min Range: -8.5017
Max Act: 8.5017. Min Act: -0.1700
Data Index: 2388928 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5017. Min Range: -8.5017
Max Act: 8.4392. Min Act: -0.1700
Data Index: 444742 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5017. Min Range: -8.5017
Max Act: 8.3142. Min Act: -0.1700
Data Index: 2320503 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5017. Min Range: -8.5017
Max Act: 8.1892. Min Act: -0.1700
Data Index: 6461263 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5017. Min Range: -8.5017
Max Act: 8.1892. Min Act: -0.1700
Data Index: 2669623 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5017. Min Range: -8.5017
Max Act: 8.1892. Min Act: -0.1700
Data Index: 8064277 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5017. Min Range: -8.5017
Max Act: 8.1892. Min Act: -0.1700
Data Index: 1889982 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5017. Min Range: -8.5017
Max Act: 8.1267. Min Act: -0.1700
Data Index: 2398004 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5017. Min Range: -8.5017
Max Act: 8.1267. Min Act: -0.1700
Data Index: 501056 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5017. Min Range: -8.5017
Max Act: 8.1267. Min Act: -0.1700
Data Index: 8226662 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5017. Min Range: -8.5017
Max Act: 8.0642. Min Act: -0.1700
Data Index: 4338766 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5017. Min Range: -8.5017
Max Act: 8.0642. Min Act: -0.1700
Data Index: 1536388 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5017. Min Range: -8.5017
Max Act: 8.0330. Min Act: -0.1700
Data Index: 5018519 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5017. Min Range: -8.5017
Max Act: 8.0642. Min Act: -0.1700
Data Index: 2254521 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5017. Min Range: -8.5017
Max Act: 8.0017. Min Act: -0.1700
Data Index: 1232687 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5017. Min Range: -8.5017
Max Act: 7.9705. Min Act: -0.1700
Data Index: 3681518 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5017. Min Range: -8.5017
Max Act: 7.9392. Min Act: -0.1700
Data Index: 5882915 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5017. Min Range: -8.5017
Max Act: 7.9080. Min Act: -0.1700
Data Index: 2318364 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5017. Min Range: -8.5017
Max Act: 7.9392. Min Act: -0.1700
Data Index: 6238266 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5017. Min Range: -8.5017
Max Act: 7.8767. Min Act: -0.1700
Data Index: 3216156 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #19