Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 708 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9734. Min Range: -8.9734
Max Act: 8.9734. Min Act: -0.1700
Data Index: 8757459 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9734. Min Range: -8.9734
Max Act: 8.8484. Min Act: -0.1700
Data Index: 436965 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9734. Min Range: -8.9734
Max Act: 8.7234. Min Act: -0.1700
Data Index: 8090036 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9734. Min Range: -8.9734
Max Act: 8.6609. Min Act: -0.1700
Data Index: 664374 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9734. Min Range: -8.9734
Max Act: 8.5984. Min Act: -0.1700
Data Index: 1711991 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9734. Min Range: -8.9734
Max Act: 8.5984. Min Act: -0.1700
Data Index: 6776323 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9734. Min Range: -8.9734
Max Act: 8.5359. Min Act: -0.1700
Data Index: 1207071 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9734. Min Range: -8.9734
Max Act: 8.5359. Min Act: -0.1700
Data Index: 4383238 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9734. Min Range: -8.9734
Max Act: 8.5359. Min Act: -0.1700
Data Index: 796046 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9734. Min Range: -8.9734
Max Act: 8.4734. Min Act: -0.1700
Data Index: 5815236 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9734. Min Range: -8.9734
Max Act: 8.4109. Min Act: -0.1700
Data Index: 599452 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9734. Min Range: -8.9734
Max Act: 8.4109. Min Act: -0.1700
Data Index: 4308195 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9734. Min Range: -8.9734
Max Act: 8.4109. Min Act: -0.1700
Data Index: 4190152 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9734. Min Range: -8.9734
Max Act: 8.4109. Min Act: -0.1700
Data Index: 1664881 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9734. Min Range: -8.9734
Max Act: 8.4109. Min Act: -0.1700
Data Index: 6173786 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9734. Min Range: -8.9734
Max Act: 8.4109. Min Act: -0.1700
Data Index: 5954591 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9734. Min Range: -8.9734
Max Act: 8.3484. Min Act: -0.1700
Data Index: 3596632 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9734. Min Range: -8.9734
Max Act: 8.3484. Min Act: -0.1700
Data Index: 6807438 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9734. Min Range: -8.9734
Max Act: 8.3484. Min Act: -0.1700
Data Index: 7335815 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9734. Min Range: -8.9734
Max Act: 8.3484. Min Act: -0.1700
Data Index: 7893070 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #19