Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4024 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.9393. Min Range: -11.9393
Max Act: 11.9393. Min Act: -0.1700
Data Index: 1762073 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.9393. Min Range: -11.9393
Max Act: 11.8143. Min Act: -0.1700
Data Index: 6632726 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.9393. Min Range: -11.9393
Max Act: 10.7518. Min Act: -0.1700
Data Index: 2117712 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.9393. Min Range: -11.9393
Max Act: 10.6268. Min Act: -0.1700
Data Index: 8164718 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.9393. Min Range: -11.9393
Max Act: 10.5643. Min Act: -0.1700
Data Index: 7581097 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.9393. Min Range: -11.9393
Max Act: 10.5018. Min Act: -0.1700
Data Index: 3323093 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.9393. Min Range: -11.9393
Max Act: 10.5018. Min Act: -0.1700
Data Index: 7906335 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.9393. Min Range: -11.9393
Max Act: 10.4393. Min Act: -0.1700
Data Index: 3862206 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.9393. Min Range: -11.9393
Max Act: 10.3768. Min Act: -0.1700
Data Index: 7040933 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.9393. Min Range: -11.9393
Max Act: 10.3143. Min Act: -0.1700
Data Index: 5785215 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.9393. Min Range: -11.9393
Max Act: 10.3143. Min Act: -0.1700
Data Index: 3705738 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.9393. Min Range: -11.9393
Max Act: 10.2518. Min Act: -0.1700
Data Index: 1250 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.9393. Min Range: -11.9393
Max Act: 10.2518. Min Act: -0.1700
Data Index: 5163718 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.9393. Min Range: -11.9393
Max Act: 10.2518. Min Act: -0.1700
Data Index: 8377122 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.9393. Min Range: -11.9393
Max Act: 10.2518. Min Act: -0.1700
Data Index: 4544996 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.9393. Min Range: -11.9393
Max Act: 10.2518. Min Act: -0.1700
Data Index: 7053546 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.9393. Min Range: -11.9393
Max Act: 10.0643. Min Act: -0.1700
Data Index: 4594378 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.9393. Min Range: -11.9393
Max Act: 10.0018. Min Act: -0.1700
Data Index: 7883962 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.9393. Min Range: -11.9393
Max Act: 10.0643. Min Act: -0.1700
Data Index: 7767535 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.9393. Min Range: -11.9393
Max Act: 10.0643. Min Act: -0.1700
Data Index: 1225588 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #19