Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2278 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4211. Min Range: -3.4211
Max Act: 3.4211. Min Act: -0.1700
Data Index: 1569868 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4211. Min Range: -3.4211
Max Act: 3.3740. Min Act: -0.1700
Data Index: 2234830 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4211. Min Range: -3.4211
Max Act: 3.3897. Min Act: -0.1700
Data Index: 4959248 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4211. Min Range: -3.4211
Max Act: 3.3897. Min Act: -0.1700
Data Index: 6304746 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4211. Min Range: -3.4211
Max Act: 3.3583. Min Act: -0.1700
Data Index: 8669992 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4211. Min Range: -3.4211
Max Act: 3.3740. Min Act: -0.1700
Data Index: 3091901 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4211. Min Range: -3.4211
Max Act: 3.3583. Min Act: -0.1700
Data Index: 7438419 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4211. Min Range: -3.4211
Max Act: 3.3270. Min Act: -0.1700
Data Index: 4278889 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4211. Min Range: -3.4211
Max Act: 3.2956. Min Act: -0.1700
Data Index: 8680533 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4211. Min Range: -3.4211
Max Act: 3.2956. Min Act: -0.1700
Data Index: 5284480 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4211. Min Range: -3.4211
Max Act: 3.2956. Min Act: -0.1700
Data Index: 2211458 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4211. Min Range: -3.4211
Max Act: 3.2956. Min Act: -0.1700
Data Index: 8820096 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4211. Min Range: -3.4211
Max Act: 3.2956. Min Act: -0.1700
Data Index: 1569869 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4211. Min Range: -3.4211
Max Act: 3.2956. Min Act: -0.1700
Data Index: 586435 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4211. Min Range: -3.4211
Max Act: 3.2642. Min Act: -0.1700
Data Index: 1690687 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4211. Min Range: -3.4211
Max Act: 3.2799. Min Act: -0.1700
Data Index: 5295736 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4211. Min Range: -3.4211
Max Act: 3.2956. Min Act: -0.1700
Data Index: 971096 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4211. Min Range: -3.4211
Max Act: 3.2642. Min Act: -0.1700
Data Index: 3415594 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4211. Min Range: -3.4211
Max Act: 3.2642. Min Act: -0.1700
Data Index: 8783212 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4211. Min Range: -3.4211
Max Act: 3.2642. Min Act: -0.1700
Data Index: 3490709 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #19