Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2346 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.7648. Min Range: -2.7648
Max Act: 2.7648. Min Act: -0.1700
Data Index: 2504896 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7648. Min Range: -2.7648
Max Act: 2.7329. Min Act: -0.1700
Data Index: 7439235 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7648. Min Range: -2.7648
Max Act: 2.6849. Min Act: -0.1700
Data Index: 6840883 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7648. Min Range: -2.7648
Max Act: 2.6689. Min Act: -0.1700
Data Index: 2646936 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7648. Min Range: -2.7648
Max Act: 2.6528. Min Act: -0.1700
Data Index: 4316967 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7648. Min Range: -2.7648
Max Act: 2.6368. Min Act: -0.1700
Data Index: 6926590 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7648. Min Range: -2.7648
Max Act: 2.6046. Min Act: -0.1700
Data Index: 7872203 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7648. Min Range: -2.7648
Max Act: 2.6207. Min Act: -0.1700
Data Index: 6358748 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7648. Min Range: -2.7648
Max Act: 2.6207. Min Act: -0.1700
Data Index: 553032 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7648. Min Range: -2.7648
Max Act: 2.5885. Min Act: -0.1700
Data Index: 2369891 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7648. Min Range: -2.7648
Max Act: 2.5724. Min Act: -0.1700
Data Index: 6526567 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7648. Min Range: -2.7648
Max Act: 2.5724. Min Act: -0.1700
Data Index: 6842086 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7648. Min Range: -2.7648
Max Act: 2.5240. Min Act: -0.1700
Data Index: 4819431 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7648. Min Range: -2.7648
Max Act: 2.5401. Min Act: -0.1700
Data Index: 3612153 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7648. Min Range: -2.7648
Max Act: 2.5240. Min Act: -0.1700
Data Index: 4096939 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7648. Min Range: -2.7648
Max Act: 2.5401. Min Act: -0.1700
Data Index: 1359525 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7648. Min Range: -2.7648
Max Act: 2.5401. Min Act: -0.1700
Data Index: 7381017 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7648. Min Range: -2.7648
Max Act: 2.5401. Min Act: -0.1700
Data Index: 6219719 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7648. Min Range: -2.7648
Max Act: 2.5401. Min Act: -0.1700
Data Index: 3963011 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7648. Min Range: -2.7648
Max Act: 2.5401. Min Act: -0.1700
Data Index: 541654 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #19