Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2256 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1241. Min Range: -5.1241
Max Act: 5.1241. Min Act: -0.1700
Data Index: 8061876 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1241. Min Range: -5.1241
Max Act: 5.0616. Min Act: -0.1700
Data Index: 4507728 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1241. Min Range: -5.1241
Max Act: 5.0616. Min Act: -0.1700
Data Index: 2479785 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1241. Min Range: -5.1241
Max Act: 5.0303. Min Act: -0.1700
Data Index: 5913340 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1241. Min Range: -5.1241
Max Act: 5.0303. Min Act: -0.1700
Data Index: 1699214 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1241. Min Range: -5.1241
Max Act: 4.9678. Min Act: -0.1700
Data Index: 4776596 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1241. Min Range: -5.1241
Max Act: 4.9678. Min Act: -0.1700
Data Index: 2257228 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1241. Min Range: -5.1241
Max Act: 4.9678. Min Act: -0.1700
Data Index: 5628073 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1241. Min Range: -5.1241
Max Act: 4.9678. Min Act: -0.1700
Data Index: 8615461 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1241. Min Range: -5.1241
Max Act: 4.9366. Min Act: -0.1700
Data Index: 4640405 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1241. Min Range: -5.1241
Max Act: 4.9366. Min Act: -0.1700
Data Index: 412684 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1241. Min Range: -5.1241
Max Act: 4.8741. Min Act: -0.1700
Data Index: 3124207 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1241. Min Range: -5.1241
Max Act: 4.9053. Min Act: -0.1700
Data Index: 1377846 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1241. Min Range: -5.1241
Max Act: 4.9053. Min Act: -0.1700
Data Index: 3329655 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1241. Min Range: -5.1241
Max Act: 4.9053. Min Act: -0.1700
Data Index: 2813822 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1241. Min Range: -5.1241
Max Act: 4.9053. Min Act: -0.1700
Data Index: 6911155 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1241. Min Range: -5.1241
Max Act: 4.9053. Min Act: -0.1700
Data Index: 3283191 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1241. Min Range: -5.1241
Max Act: 4.9053. Min Act: -0.1699
Data Index: 1710855 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1241. Min Range: -5.1241
Max Act: 4.8741. Min Act: -0.1700
Data Index: 5025518 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1241. Min Range: -5.1241
Max Act: 4.9053. Min Act: -0.1700
Data Index: 5109523 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #19