Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1503 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0690. Min Range: -8.0690
Max Act: 8.0690. Min Act: -0.1700
Data Index: 7342983 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0690. Min Range: -8.0690
Max Act: 7.1940. Min Act: -0.1700
Data Index: 4274738 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0690. Min Range: -8.0690
Max Act: 7.1628. Min Act: -0.1700
Data Index: 4062561 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0690. Min Range: -8.0690
Max Act: 7.0690. Min Act: -0.1700
Data Index: 2874815 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0690. Min Range: -8.0690
Max Act: 7.0690. Min Act: -0.1700
Data Index: 2880298 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0690. Min Range: -8.0690
Max Act: 6.9440. Min Act: -0.1700
Data Index: 1552561 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0690. Min Range: -8.0690
Max Act: 6.9440. Min Act: -0.1700
Data Index: 4062562 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0690. Min Range: -8.0690
Max Act: 6.8503. Min Act: -0.1700
Data Index: 925547 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0690. Min Range: -8.0690
Max Act: 6.8815. Min Act: -0.1700
Data Index: 6266372 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0690. Min Range: -8.0690
Max Act: 6.8815. Min Act: -0.1700
Data Index: 3730370 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0690. Min Range: -8.0690
Max Act: 6.8815. Min Act: -0.1700
Data Index: 2410618 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0690. Min Range: -8.0690
Max Act: 6.7878. Min Act: -0.1700
Data Index: 462818 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0690. Min Range: -8.0690
Max Act: 6.7878. Min Act: -0.1700
Data Index: 1648394 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0690. Min Range: -8.0690
Max Act: 6.7565. Min Act: -0.1700
Data Index: 606842 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0690. Min Range: -8.0690
Max Act: 6.7253. Min Act: -0.1700
Data Index: 7682580 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0690. Min Range: -8.0690
Max Act: 6.7565. Min Act: -0.1700
Data Index: 49554 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0690. Min Range: -8.0690
Max Act: 6.7253. Min Act: -0.1700
Data Index: 831841 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0690. Min Range: -8.0690
Max Act: 6.6940. Min Act: -0.1700
Data Index: 3189378 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0690. Min Range: -8.0690
Max Act: 6.6628. Min Act: -0.1700
Data Index: 6348532 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0690. Min Range: -8.0690
Max Act: 6.6628. Min Act: -0.1700
Data Index: 1146298 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #19