Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2018 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7253. Min Range: -6.7253
Max Act: 6.7253. Min Act: -0.1700
Data Index: 5201171 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7253. Min Range: -6.7253
Max Act: 6.5065. Min Act: -0.1700
Data Index: 3619872 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7253. Min Range: -6.7253
Max Act: 6.5065. Min Act: -0.1700
Data Index: 7936750 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7253. Min Range: -6.7253
Max Act: 6.4753. Min Act: -0.1700
Data Index: 6203758 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7253. Min Range: -6.7253
Max Act: 6.4128. Min Act: -0.1700
Data Index: 6042795 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7253. Min Range: -6.7253
Max Act: 6.4128. Min Act: -0.1700
Data Index: 6089521 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7253. Min Range: -6.7253
Max Act: 6.2878. Min Act: -0.1700
Data Index: 731657 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7253. Min Range: -6.7253
Max Act: 6.2878. Min Act: -0.1700
Data Index: 6884125 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7253. Min Range: -6.7253
Max Act: 6.2253. Min Act: -0.1700
Data Index: 7024250 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7253. Min Range: -6.7253
Max Act: 6.2878. Min Act: -0.1700
Data Index: 6235002 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7253. Min Range: -6.7253
Max Act: 6.2253. Min Act: -0.1700
Data Index: 4368457 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7253. Min Range: -6.7253
Max Act: 6.2253. Min Act: -0.1700
Data Index: 6252955 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7253. Min Range: -6.7253
Max Act: 6.1940. Min Act: -0.1700
Data Index: 2622586 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7253. Min Range: -6.7253
Max Act: 6.1628. Min Act: -0.1700
Data Index: 361669 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7253. Min Range: -6.7253
Max Act: 6.1628. Min Act: -0.1700
Data Index: 7765555 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7253. Min Range: -6.7253
Max Act: 6.1003. Min Act: -0.1700
Data Index: 943830 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7253. Min Range: -6.7253
Max Act: 6.1315. Min Act: -0.1700
Data Index: 8084301 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7253. Min Range: -6.7253
Max Act: 6.0690. Min Act: -0.1700
Data Index: 1860723 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7253. Min Range: -6.7253
Max Act: 6.0690. Min Act: -0.1700
Data Index: 4426762 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7253. Min Range: -6.7253
Max Act: 6.0690. Min Act: -0.1700
Data Index: 6362504 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #19