Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2563 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7574. Min Range: -3.7574
Max Act: 3.7574. Min Act: -0.1700
Data Index: 1120400 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7574. Min Range: -3.7574
Max Act: 3.7574. Min Act: -0.1700
Data Index: 4652193 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7574. Min Range: -3.7574
Max Act: 3.6635. Min Act: -0.1700
Data Index: 6030565 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7574. Min Range: -3.7574
Max Act: 3.6322. Min Act: -0.1700
Data Index: 5504769 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7574. Min Range: -3.7574
Max Act: 3.6322. Min Act: -0.1700
Data Index: 8095180 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7574. Min Range: -3.7574
Max Act: 3.6322. Min Act: -0.1700
Data Index: 5071413 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7574. Min Range: -3.7574
Max Act: 3.6009. Min Act: -0.1700
Data Index: 8418574 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7574. Min Range: -3.7574
Max Act: 3.6166. Min Act: -0.1700
Data Index: 7765657 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7574. Min Range: -3.7574
Max Act: 3.5540. Min Act: -0.1700
Data Index: 4330424 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7574. Min Range: -3.7574
Max Act: 3.5696. Min Act: -0.1700
Data Index: 4268979 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7574. Min Range: -3.7574
Max Act: 3.5383. Min Act: -0.1700
Data Index: 7432571 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7574. Min Range: -3.7574
Max Act: 3.5227. Min Act: -0.1700
Data Index: 2216463 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7574. Min Range: -3.7574
Max Act: 3.5227. Min Act: -0.1700
Data Index: 6450729 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7574. Min Range: -3.7574
Max Act: 3.5383. Min Act: -0.1700
Data Index: 3074443 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7574. Min Range: -3.7574
Max Act: 3.5227. Min Act: -0.1700
Data Index: 5901609 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7574. Min Range: -3.7574
Max Act: 3.5070. Min Act: -0.1700
Data Index: 6746146 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7574. Min Range: -3.7574
Max Act: 3.5070. Min Act: -0.1700
Data Index: 2871271 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7574. Min Range: -3.7574
Max Act: 3.5227. Min Act: -0.1700
Data Index: 2259561 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7574. Min Range: -3.7574
Max Act: 3.5227. Min Act: -0.1700
Data Index: 8188834 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7574. Min Range: -3.7574
Max Act: 3.4913. Min Act: -0.1700
Data Index: 1043010 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #19