Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 850 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0731. Min Range: -5.0731
Max Act: 5.0731. Min Act: -0.1700
Data Index: 962937 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0731. Min Range: -5.0731
Max Act: 4.9794. Min Act: -0.1700
Data Index: 6725307 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0731. Min Range: -5.0731
Max Act: 4.9481. Min Act: -0.1700
Data Index: 656771 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0731. Min Range: -5.0731
Max Act: 4.7919. Min Act: -0.1700
Data Index: 140788 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0731. Min Range: -5.0731
Max Act: 4.7919. Min Act: -0.1700
Data Index: 2888706 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0731. Min Range: -5.0731
Max Act: 4.7606. Min Act: -0.1700
Data Index: 2994047 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0731. Min Range: -5.0731
Max Act: 4.7606. Min Act: -0.1700
Data Index: 4953571 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0731. Min Range: -5.0731
Max Act: 4.6981. Min Act: -0.1700
Data Index: 5460408 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0731. Min Range: -5.0731
Max Act: 4.7294. Min Act: -0.1700
Data Index: 2764625 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0731. Min Range: -5.0731
Max Act: 4.6981. Min Act: -0.1700
Data Index: 6614787 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0731. Min Range: -5.0731
Max Act: 4.6981. Min Act: -0.1700
Data Index: 2826968 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0731. Min Range: -5.0731
Max Act: 4.6669. Min Act: -0.1700
Data Index: 4043722 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0731. Min Range: -5.0731
Max Act: 4.6669. Min Act: -0.1700
Data Index: 1187974 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0731. Min Range: -5.0731
Max Act: 4.6669. Min Act: -0.1700
Data Index: 175581 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0731. Min Range: -5.0731
Max Act: 4.6981. Min Act: -0.1700
Data Index: 6722418 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0731. Min Range: -5.0731
Max Act: 4.6669. Min Act: -0.1700
Data Index: 8070465 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0731. Min Range: -5.0731
Max Act: 4.6356. Min Act: -0.1700
Data Index: 3919797 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0731. Min Range: -5.0731
Max Act: 4.6356. Min Act: -0.1700
Data Index: 4075163 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0731. Min Range: -5.0731
Max Act: 4.6356. Min Act: -0.1700
Data Index: 177450 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0731. Min Range: -5.0731
Max Act: 4.6356. Min Act: -0.1700
Data Index: 1214792 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19