Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5017 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4521. Min Range: -9.4521
Max Act: 9.4521. Min Act: -0.1700
Data Index: 723594 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4521. Min Range: -9.4521
Max Act: 9.3271. Min Act: -0.1700
Data Index: 6370925 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4521. Min Range: -9.4521
Max Act: 9.0771. Min Act: -0.1700
Data Index: 2696016 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4521. Min Range: -9.4521
Max Act: 9.0146. Min Act: -0.1700
Data Index: 1757463 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4521. Min Range: -9.4521
Max Act: 8.9521. Min Act: -0.1700
Data Index: 7888175 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4521. Min Range: -9.4521
Max Act: 8.8896. Min Act: -0.1700
Data Index: 3157876 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4521. Min Range: -9.4521
Max Act: 8.8271. Min Act: -0.1700
Data Index: 6208105 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4521. Min Range: -9.4521
Max Act: 8.8271. Min Act: -0.1700
Data Index: 1639598 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4521. Min Range: -9.4521
Max Act: 8.7646. Min Act: -0.1700
Data Index: 2921807 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4521. Min Range: -9.4521
Max Act: 8.7646. Min Act: -0.1700
Data Index: 2740850 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4521. Min Range: -9.4521
Max Act: 8.7646. Min Act: -0.1700
Data Index: 1225277 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4521. Min Range: -9.4521
Max Act: 8.7646. Min Act: -0.1700
Data Index: 8721509 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4521. Min Range: -9.4521
Max Act: 8.7646. Min Act: -0.1700
Data Index: 1944454 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4521. Min Range: -9.4521
Max Act: 8.7021. Min Act: -0.1700
Data Index: 7001487 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4521. Min Range: -9.4521
Max Act: 8.7021. Min Act: -0.1700
Data Index: 3815607 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4521. Min Range: -9.4521
Max Act: 8.6396. Min Act: -0.1700
Data Index: 6390726 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4521. Min Range: -9.4521
Max Act: 8.7021. Min Act: -0.1700
Data Index: 5094747 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4521. Min Range: -9.4521
Max Act: 8.6396. Min Act: -0.1700
Data Index: 7316476 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4521. Min Range: -9.4521
Max Act: 8.5771. Min Act: -0.1700
Data Index: 6480328 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4521. Min Range: -9.4521
Max Act: 8.5771. Min Act: -0.1700
Data Index: 6038921 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #19