Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2622 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7253. Min Range: -4.7253
Max Act: 4.7253. Min Act: -0.1700
Data Index: 6354550 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7253. Min Range: -4.7253
Max Act: 4.5378. Min Act: -0.1700
Data Index: 334142 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7253. Min Range: -4.7253
Max Act: 4.4753. Min Act: -0.1700
Data Index: 6634780 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7253. Min Range: -4.7253
Max Act: 4.4441. Min Act: -0.1700
Data Index: 6801019 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7253. Min Range: -4.7253
Max Act: 4.4128. Min Act: -0.1700
Data Index: 3570766 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7253. Min Range: -4.7253
Max Act: 4.3816. Min Act: -0.1700
Data Index: 3623082 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7253. Min Range: -4.7253
Max Act: 4.3503. Min Act: -0.1700
Data Index: 4903423 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7253. Min Range: -4.7253
Max Act: 4.3191. Min Act: -0.1700
Data Index: 557007 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7253. Min Range: -4.7253
Max Act: 4.3191. Min Act: -0.1700
Data Index: 3944748 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7253. Min Range: -4.7253
Max Act: 4.3191. Min Act: -0.1700
Data Index: 577862 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7253. Min Range: -4.7253
Max Act: 4.2878. Min Act: -0.1700
Data Index: 5972354 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7253. Min Range: -4.7253
Max Act: 4.2878. Min Act: -0.1700
Data Index: 4232999 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7253. Min Range: -4.7253
Max Act: 4.2566. Min Act: -0.1700
Data Index: 2030154 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7253. Min Range: -4.7253
Max Act: 4.2253. Min Act: -0.1700
Data Index: 4090846 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7253. Min Range: -4.7253
Max Act: 4.1941. Min Act: -0.1700
Data Index: 3885954 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7253. Min Range: -4.7253
Max Act: 4.1941. Min Act: -0.1700
Data Index: 2062991 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7253. Min Range: -4.7253
Max Act: 4.1628. Min Act: -0.1700
Data Index: 3438386 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7253. Min Range: -4.7253
Max Act: 4.1628. Min Act: -0.1700
Data Index: 2227716 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7253. Min Range: -4.7253
Max Act: 4.1628. Min Act: -0.1700
Data Index: 4312880 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7253. Min Range: -4.7253
Max Act: 4.1628. Min Act: -0.1700
Data Index: 4681557 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #19