Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3793 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1906. Min Range: -9.1906
Max Act: 9.1906. Min Act: -0.1700
Data Index: 8443391 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1906. Min Range: -9.1906
Max Act: 9.1281. Min Act: -0.1700
Data Index: 4336947 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1906. Min Range: -9.1906
Max Act: 9.0656. Min Act: -0.1700
Data Index: 7206333 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1906. Min Range: -9.1906
Max Act: 9.0656. Min Act: -0.1695
Data Index: 6320538 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1906. Min Range: -9.1906
Max Act: 9.0031. Min Act: -0.1699
Data Index: 1832642 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1906. Min Range: -9.1906
Max Act: 8.9406. Min Act: -0.1700
Data Index: 1987947 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1906. Min Range: -9.1906
Max Act: 8.8781. Min Act: -0.1700
Data Index: 4046774 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1906. Min Range: -9.1906
Max Act: 8.8156. Min Act: -0.1700
Data Index: 7340853 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1906. Min Range: -9.1906
Max Act: 8.8156. Min Act: -0.1700
Data Index: 3235287 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1906. Min Range: -9.1906
Max Act: 8.8156. Min Act: -0.1700
Data Index: 3235288 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1906. Min Range: -9.1906
Max Act: 8.8156. Min Act: -0.1700
Data Index: 1832641 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1906. Min Range: -9.1906
Max Act: 8.7531. Min Act: -0.1700
Data Index: 4252585 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1906. Min Range: -9.1906
Max Act: 8.7531. Min Act: -0.1700
Data Index: 1044778 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1906. Min Range: -9.1906
Max Act: 8.7531. Min Act: -0.1700
Data Index: 2701018 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1906. Min Range: -9.1906
Max Act: 8.6906. Min Act: -0.1700
Data Index: 5273257 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1906. Min Range: -9.1906
Max Act: 8.6906. Min Act: -0.1700
Data Index: 4279106 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1906. Min Range: -9.1906
Max Act: 8.6906. Min Act: -0.1700
Data Index: 4252589 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1906. Min Range: -9.1906
Max Act: 8.6906. Min Act: -0.1700
Data Index: 1832643 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1906. Min Range: -9.1906
Max Act: 8.6281. Min Act: -0.1700
Data Index: 4691471 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1906. Min Range: -9.1906
Max Act: 8.5656. Min Act: -0.1700
Data Index: 1560916 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #19