Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1890 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1687. Min Range: -7.1687
Max Act: 7.1687. Min Act: -0.1700
Data Index: 954241 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1687. Min Range: -7.1687
Max Act: 7.1687. Min Act: -0.1700
Data Index: 1790633 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1687. Min Range: -7.1687
Max Act: 7.1062. Min Act: -0.1700
Data Index: 7010554 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1687. Min Range: -7.1687
Max Act: 6.9499. Min Act: -0.1700
Data Index: 4298851 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1687. Min Range: -7.1687
Max Act: 6.9187. Min Act: -0.1700
Data Index: 4298837 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1687. Min Range: -7.1687
Max Act: 6.9499. Min Act: -0.1700
Data Index: 5281985 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1687. Min Range: -7.1687
Max Act: 6.8874. Min Act: -0.1700
Data Index: 3386380 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1687. Min Range: -7.1687
Max Act: 6.9187. Min Act: -0.1700
Data Index: 8002298 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1687. Min Range: -7.1687
Max Act: 6.9187. Min Act: -0.1700
Data Index: 3513384 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1687. Min Range: -7.1687
Max Act: 6.8874. Min Act: -0.1700
Data Index: 4043234 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1687. Min Range: -7.1687
Max Act: 6.8562. Min Act: -0.1700
Data Index: 2371094 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1687. Min Range: -7.1687
Max Act: 6.8249. Min Act: -0.1700
Data Index: 7790392 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1687. Min Range: -7.1687
Max Act: 6.8249. Min Act: -0.1700
Data Index: 3414912 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1687. Min Range: -7.1687
Max Act: 6.7937. Min Act: -0.1700
Data Index: 3414914 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1687. Min Range: -7.1687
Max Act: 6.7937. Min Act: -0.1700
Data Index: 2343817 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1687. Min Range: -7.1687
Max Act: 6.7937. Min Act: -0.1700
Data Index: 22681 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1687. Min Range: -7.1687
Max Act: 6.7624. Min Act: -0.1700
Data Index: 4250387 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1687. Min Range: -7.1687
Max Act: 6.6687. Min Act: -0.1700
Data Index: 2081195 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1687. Min Range: -7.1687
Max Act: 6.6687. Min Act: -0.1700
Data Index: 4577860 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1687. Min Range: -7.1687
Max Act: 6.6687. Min Act: -0.1700
Data Index: 7084016 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #19