Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5846 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4731. Min Range: -5.4731
Max Act: 5.4731. Min Act: -0.1700
Data Index: 8081415 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4731. Min Range: -5.4731
Max Act: 5.3169. Min Act: -0.1700
Data Index: 4255857 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4731. Min Range: -5.4731
Max Act: 5.3169. Min Act: -0.1700
Data Index: 6819451 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4731. Min Range: -5.4731
Max Act: 5.2856. Min Act: -0.1700
Data Index: 5931236 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4731. Min Range: -5.4731
Max Act: 5.1919. Min Act: -0.1700
Data Index: 7475783 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4731. Min Range: -5.4731
Max Act: 5.1606. Min Act: -0.1700
Data Index: 6819450 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4731. Min Range: -5.4731
Max Act: 5.1606. Min Act: -0.1700
Data Index: 5159824 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4731. Min Range: -5.4731
Max Act: 5.1606. Min Act: -0.1700
Data Index: 4842211 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4731. Min Range: -5.4731
Max Act: 5.1294. Min Act: -0.1700
Data Index: 5094739 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4731. Min Range: -5.4731
Max Act: 5.0981. Min Act: -0.1700
Data Index: 7475786 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4731. Min Range: -5.4731
Max Act: 5.0981. Min Act: -0.1700
Data Index: 8366520 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4731. Min Range: -5.4731
Max Act: 5.0981. Min Act: -0.1700
Data Index: 4868409 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4731. Min Range: -5.4731
Max Act: 5.0356. Min Act: -0.1700
Data Index: 811949 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4731. Min Range: -5.4731
Max Act: 5.0044. Min Act: -0.1700
Data Index: 939703 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4731. Min Range: -5.4731
Max Act: 5.0044. Min Act: -0.1700
Data Index: 5713659 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4731. Min Range: -5.4731
Max Act: 5.0044. Min Act: -0.1700
Data Index: 5454538 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4731. Min Range: -5.4731
Max Act: 5.0044. Min Act: -0.1700
Data Index: 1083482 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4731. Min Range: -5.4731
Max Act: 4.9731. Min Act: -0.1700
Data Index: 1451387 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4731. Min Range: -5.4731
Max Act: 4.9419. Min Act: -0.1700
Data Index: 4074191 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4731. Min Range: -5.4731
Max Act: 4.9731. Min Act: -0.1700
Data Index: 7475772 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #19