Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4410 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4267. Min Range: -8.4267
Max Act: 8.4267. Min Act: -0.1700
Data Index: 3261268 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4267. Min Range: -8.4267
Max Act: 8.2392. Min Act: -0.1700
Data Index: 7351791 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4267. Min Range: -8.4267
Max Act: 8.0517. Min Act: -0.1700
Data Index: 888239 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4267. Min Range: -8.4267
Max Act: 7.9892. Min Act: -0.1700
Data Index: 1268823 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4267. Min Range: -8.4267
Max Act: 8.0517. Min Act: -0.1700
Data Index: 3652975 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4267. Min Range: -8.4267
Max Act: 7.9892. Min Act: -0.1700
Data Index: 911668 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4267. Min Range: -8.4267
Max Act: 7.9267. Min Act: -0.1700
Data Index: 6214690 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4267. Min Range: -8.4267
Max Act: 7.8642. Min Act: -0.1700
Data Index: 2822581 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4267. Min Range: -8.4267
Max Act: 7.8642. Min Act: -0.1700
Data Index: 1204875 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4267. Min Range: -8.4267
Max Act: 7.8642. Min Act: -0.1700
Data Index: 3090830 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4267. Min Range: -8.4267
Max Act: 7.8017. Min Act: -0.1700
Data Index: 7213922 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4267. Min Range: -8.4267
Max Act: 7.7392. Min Act: -0.1700
Data Index: 65472 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4267. Min Range: -8.4267
Max Act: 7.7392. Min Act: -0.1700
Data Index: 1874333 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4267. Min Range: -8.4267
Max Act: 7.7392. Min Act: -0.1700
Data Index: 4665823 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4267. Min Range: -8.4267
Max Act: 7.6767. Min Act: -0.1700
Data Index: 6646618 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4267. Min Range: -8.4267
Max Act: 7.8017. Min Act: -0.1700
Data Index: 8233353 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4267. Min Range: -8.4267
Max Act: 7.7392. Min Act: -0.1700
Data Index: 7519351 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4267. Min Range: -8.4267
Max Act: 7.7392. Min Act: -0.1700
Data Index: 1222074 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4267. Min Range: -8.4267
Max Act: 7.7392. Min Act: -0.1700
Data Index: 1990764 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4267. Min Range: -8.4267
Max Act: 7.6767. Min Act: -0.1700
Data Index: 2096761 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #19