Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1453 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5135. Min Range: -8.5135
Max Act: 8.5135. Min Act: -0.1700
Data Index: 223289 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5135. Min Range: -8.5135
Max Act: 8.3885. Min Act: -0.1700
Data Index: 4054272 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5135. Min Range: -8.5135
Max Act: 8.3260. Min Act: -0.1700
Data Index: 5969986 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5135. Min Range: -8.5135
Max Act: 8.2010. Min Act: -0.1700
Data Index: 822010 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5135. Min Range: -8.5135
Max Act: 8.1385. Min Act: -0.1700
Data Index: 5402411 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5135. Min Range: -8.5135
Max Act: 8.1385. Min Act: -0.1700
Data Index: 4858296 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5135. Min Range: -8.5135
Max Act: 8.0760. Min Act: -0.1700
Data Index: 6057884 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5135. Min Range: -8.5135
Max Act: 8.0760. Min Act: -0.1700
Data Index: 6180795 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5135. Min Range: -8.5135
Max Act: 8.0760. Min Act: -0.1700
Data Index: 5281373 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5135. Min Range: -8.5135
Max Act: 8.0760. Min Act: -0.1700
Data Index: 5823867 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5135. Min Range: -8.5135
Max Act: 8.0135. Min Act: -0.1700
Data Index: 3887649 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5135. Min Range: -8.5135
Max Act: 8.0135. Min Act: -0.1700
Data Index: 1603180 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5135. Min Range: -8.5135
Max Act: 8.0135. Min Act: -0.1700
Data Index: 2602292 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5135. Min Range: -8.5135
Max Act: 7.8885. Min Act: -0.1700
Data Index: 5077449 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5135. Min Range: -8.5135
Max Act: 7.9510. Min Act: -0.1700
Data Index: 5604579 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5135. Min Range: -8.5135
Max Act: 7.8885. Min Act: -0.1700
Data Index: 3602161 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5135. Min Range: -8.5135
Max Act: 7.8885. Min Act: -0.1700
Data Index: 127289 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5135. Min Range: -8.5135
Max Act: 7.8885. Min Act: -0.1700
Data Index: 3218236 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5135. Min Range: -8.5135
Max Act: 7.8885. Min Act: -0.1700
Data Index: 4512983 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5135. Min Range: -8.5135
Max Act: 7.8885. Min Act: -0.1700
Data Index: 1580099 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #19