Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 649 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5495. Min Range: -4.5495
Max Act: 4.5495. Min Act: -0.1700
Data Index: 3550924 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5495. Min Range: -4.5495
Max Act: 4.5182. Min Act: -0.1700
Data Index: 6879088 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5495. Min Range: -4.5495
Max Act: 4.5182. Min Act: -0.1700
Data Index: 8582596 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5495. Min Range: -4.5495
Max Act: 4.3932. Min Act: -0.1700
Data Index: 4620251 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5495. Min Range: -4.5495
Max Act: 4.3620. Min Act: -0.1700
Data Index: 2458824 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5495. Min Range: -4.5495
Max Act: 4.3307. Min Act: -0.1700
Data Index: 7517710 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5495. Min Range: -4.5495
Max Act: 4.3307. Min Act: -0.1700
Data Index: 1155449 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5495. Min Range: -4.5495
Max Act: 4.3307. Min Act: -0.1700
Data Index: 4207616 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5495. Min Range: -4.5495
Max Act: 4.2995. Min Act: -0.1700
Data Index: 2458823 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5495. Min Range: -4.5495
Max Act: 4.2995. Min Act: -0.1700
Data Index: 184696 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5495. Min Range: -4.5495
Max Act: 4.2682. Min Act: -0.1700
Data Index: 780581 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5495. Min Range: -4.5495
Max Act: 4.2682. Min Act: -0.1700
Data Index: 5332069 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5495. Min Range: -4.5495
Max Act: 4.2682. Min Act: -0.1700
Data Index: 4848252 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5495. Min Range: -4.5495
Max Act: 4.2682. Min Act: -0.1700
Data Index: 4001370 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5495. Min Range: -4.5495
Max Act: 4.2682. Min Act: -0.1700
Data Index: 8007462 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5495. Min Range: -4.5495
Max Act: 4.2995. Min Act: -0.1700
Data Index: 7428520 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5495. Min Range: -4.5495
Max Act: 4.2682. Min Act: -0.1700
Data Index: 1620708 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5495. Min Range: -4.5495
Max Act: 4.2682. Min Act: -0.1700
Data Index: 5678888 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5495. Min Range: -4.5495
Max Act: 4.2682. Min Act: -0.1700
Data Index: 5452127 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5495. Min Range: -4.5495
Max Act: 4.2370. Min Act: -0.1700
Data Index: 2950356 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #19