Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 95 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9338. Min Range: -4.9338
Max Act: 4.9338. Min Act: -0.1700
Data Index: 7094229 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9338. Min Range: -4.9338
Max Act: 4.9338. Min Act: -0.1700
Data Index: 5593899 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9338. Min Range: -4.9338
Max Act: 4.8401. Min Act: -0.1700
Data Index: 2813504 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9338. Min Range: -4.9338
Max Act: 4.8088. Min Act: -0.1700
Data Index: 448203 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9338. Min Range: -4.9338
Max Act: 4.8088. Min Act: -0.1700
Data Index: 3819087 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9338. Min Range: -4.9338
Max Act: 4.8088. Min Act: -0.1700
Data Index: 7453701 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9338. Min Range: -4.9338
Max Act: 4.8088. Min Act: -0.1700
Data Index: 36340 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9338. Min Range: -4.9338
Max Act: 4.8088. Min Act: -0.1700
Data Index: 1995052 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9338. Min Range: -4.9338
Max Act: 4.7776. Min Act: -0.1700
Data Index: 7484946 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9338. Min Range: -4.9338
Max Act: 4.7776. Min Act: -0.1700
Data Index: 4406744 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9338. Min Range: -4.9338
Max Act: 4.7776. Min Act: -0.1700
Data Index: 4487576 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9338. Min Range: -4.9338
Max Act: 4.7463. Min Act: -0.1700
Data Index: 5618746 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9338. Min Range: -4.9338
Max Act: 4.7463. Min Act: -0.1700
Data Index: 3142450 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9338. Min Range: -4.9338
Max Act: 4.7463. Min Act: -0.1700
Data Index: 2889559 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9338. Min Range: -4.9338
Max Act: 4.7463. Min Act: -0.1700
Data Index: 3819632 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9338. Min Range: -4.9338
Max Act: 4.7463. Min Act: -0.1700
Data Index: 1854802 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9338. Min Range: -4.9338
Max Act: 4.7463. Min Act: -0.1700
Data Index: 2150692 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9338. Min Range: -4.9338
Max Act: 4.7463. Min Act: -0.1700
Data Index: 4289330 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9338. Min Range: -4.9338
Max Act: 4.7463. Min Act: -0.1700
Data Index: 3804939 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9338. Min Range: -4.9338
Max Act: 4.7151. Min Act: -0.1700
Data Index: 5939730 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #19