Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 957 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5767. Min Range: -3.5767
Max Act: 3.5767. Min Act: -0.1700
Data Index: 6934044 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5767. Min Range: -3.5767
Max Act: 3.4984. Min Act: -0.1700
Data Index: 959747 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5767. Min Range: -3.5767
Max Act: 3.4514. Min Act: -0.1700
Data Index: 7082929 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5767. Min Range: -3.5767
Max Act: 3.4357. Min Act: -0.1700
Data Index: 4226167 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5767. Min Range: -3.5767
Max Act: 3.4201. Min Act: -0.1700
Data Index: 7488642 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5767. Min Range: -3.5767
Max Act: 3.4044. Min Act: -0.1700
Data Index: 2014789 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5767. Min Range: -3.5767
Max Act: 3.4201. Min Act: -0.1700
Data Index: 7876412 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5767. Min Range: -3.5767
Max Act: 3.4044. Min Act: -0.1700
Data Index: 7196736 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5767. Min Range: -3.5767
Max Act: 3.3730. Min Act: -0.1700
Data Index: 5597679 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5767. Min Range: -3.5767
Max Act: 3.3573. Min Act: -0.1700
Data Index: 5043506 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5767. Min Range: -3.5767
Max Act: 3.3730. Min Act: -0.1700
Data Index: 5518397 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5767. Min Range: -3.5767
Max Act: 3.3416. Min Act: -0.1700
Data Index: 7096754 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5767. Min Range: -3.5767
Max Act: 3.3573. Min Act: -0.1700
Data Index: 1271421 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5767. Min Range: -3.5767
Max Act: 3.3416. Min Act: -0.1700
Data Index: 5345275 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5767. Min Range: -3.5767
Max Act: 3.3260. Min Act: -0.1700
Data Index: 7938737 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5767. Min Range: -3.5767
Max Act: 3.3260. Min Act: -0.1700
Data Index: 8295376 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5767. Min Range: -3.5767
Max Act: 3.3416. Min Act: -0.1700
Data Index: 7185499 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5767. Min Range: -3.5767
Max Act: 3.3416. Min Act: -0.1700
Data Index: 1548179 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5767. Min Range: -3.5767
Max Act: 3.3573. Min Act: -0.1700
Data Index: 6263968 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5767. Min Range: -3.5767
Max Act: 3.3260. Min Act: -0.1700
Data Index: 4394221 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #19