Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 441 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6638. Min Range: -7.6638
Max Act: 7.6638. Min Act: -0.1700
Data Index: 1117483 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6638. Min Range: -7.6638
Max Act: 7.6638. Min Act: -0.1700
Data Index: 3184381 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6638. Min Range: -7.6638
Max Act: 7.0388. Min Act: -0.1700
Data Index: 7447979 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6638. Min Range: -7.6638
Max Act: 7.0388. Min Act: -0.1700
Data Index: 1261810 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6638. Min Range: -7.6638
Max Act: 7.0388. Min Act: -0.1700
Data Index: 2622898 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6638. Min Range: -7.6638
Max Act: 6.9763. Min Act: -0.1700
Data Index: 5711281 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6638. Min Range: -7.6638
Max Act: 6.8201. Min Act: -0.1700
Data Index: 3769924 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6638. Min Range: -7.6638
Max Act: 6.8201. Min Act: -0.1700
Data Index: 6638435 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6638. Min Range: -7.6638
Max Act: 6.8201. Min Act: -0.1700
Data Index: 3946893 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6638. Min Range: -7.6638
Max Act: 6.7576. Min Act: -0.1700
Data Index: 5299626 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6638. Min Range: -7.6638
Max Act: 6.7263. Min Act: -0.1700
Data Index: 7424694 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6638. Min Range: -7.6638
Max Act: 6.7263. Min Act: -0.1700
Data Index: 4698959 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6638. Min Range: -7.6638
Max Act: 6.6951. Min Act: -0.1700
Data Index: 4779906 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6638. Min Range: -7.6638
Max Act: 6.6951. Min Act: -0.1700
Data Index: 529503 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6638. Min Range: -7.6638
Max Act: 6.6638. Min Act: -0.1700
Data Index: 7987773 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6638. Min Range: -7.6638
Max Act: 6.6638. Min Act: -0.1700
Data Index: 4161227 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6638. Min Range: -7.6638
Max Act: 6.6326. Min Act: -0.1700
Data Index: 880272 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6638. Min Range: -7.6638
Max Act: 6.6326. Min Act: -0.1700
Data Index: 2856205 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6638. Min Range: -7.6638
Max Act: 6.6326. Min Act: -0.1700
Data Index: 1253745 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6638. Min Range: -7.6638
Max Act: 6.6013. Min Act: -0.1700
Data Index: 2101722 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #19