Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 781 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1310. Min Range: -7.1310
Max Act: 7.1310. Min Act: -0.1700
Data Index: 966475 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1310. Min Range: -7.1310
Max Act: 7.0373. Min Act: -0.1700
Data Index: 5682365 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1310. Min Range: -7.1310
Max Act: 6.9748. Min Act: -0.1700
Data Index: 638158 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1310. Min Range: -7.1310
Max Act: 6.8810. Min Act: -0.1700
Data Index: 25097 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1310. Min Range: -7.1310
Max Act: 6.8498. Min Act: -0.1700
Data Index: 997006 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1310. Min Range: -7.1310
Max Act: 6.7873. Min Act: -0.1700
Data Index: 4568370 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1310. Min Range: -7.1310
Max Act: 6.7248. Min Act: -0.1700
Data Index: 7776053 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1310. Min Range: -7.1310
Max Act: 6.6623. Min Act: -0.1700
Data Index: 6233024 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1310. Min Range: -7.1310
Max Act: 6.6623. Min Act: -0.1700
Data Index: 3764643 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1310. Min Range: -7.1310
Max Act: 6.5998. Min Act: -0.1700
Data Index: 1473352 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1310. Min Range: -7.1310
Max Act: 6.5685. Min Act: -0.1700
Data Index: 2534287 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1310. Min Range: -7.1310
Max Act: 6.4435. Min Act: -0.1700
Data Index: 6533204 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1310. Min Range: -7.1310
Max Act: 6.4435. Min Act: -0.1700
Data Index: 7139810 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1310. Min Range: -7.1310
Max Act: 6.4123. Min Act: -0.1700
Data Index: 3683018 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1310. Min Range: -7.1310
Max Act: 6.3810. Min Act: -0.1700
Data Index: 5768292 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1310. Min Range: -7.1310
Max Act: 6.3810. Min Act: -0.1700
Data Index: 7982661 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1310. Min Range: -7.1310
Max Act: 6.3810. Min Act: -0.1700
Data Index: 7022188 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1310. Min Range: -7.1310
Max Act: 6.3810. Min Act: -0.1700
Data Index: 840032 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1310. Min Range: -7.1310
Max Act: 6.3810. Min Act: -0.1700
Data Index: 496814 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1310. Min Range: -7.1310
Max Act: 6.3498. Min Act: -0.1700
Data Index: 2507113 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #19