Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6026 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7829. Min Range: -8.7829
Max Act: 8.7829. Min Act: -0.1700
Data Index: 972400 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7829. Min Range: -8.7829
Max Act: 8.5329. Min Act: -0.1700
Data Index: 956071 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7829. Min Range: -8.7829
Max Act: 8.4704. Min Act: -0.1700
Data Index: 8357698 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7829. Min Range: -8.7829
Max Act: 8.2829. Min Act: -0.1700
Data Index: 8529601 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7829. Min Range: -8.7829
Max Act: 8.3454. Min Act: -0.1700
Data Index: 3533730 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7829. Min Range: -8.7829
Max Act: 8.2829. Min Act: -0.1700
Data Index: 2383752 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7829. Min Range: -8.7829
Max Act: 8.2829. Min Act: -0.1700
Data Index: 5638568 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7829. Min Range: -8.7829
Max Act: 8.2204. Min Act: -0.1700
Data Index: 1664755 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7829. Min Range: -8.7829
Max Act: 8.2204. Min Act: -0.1700
Data Index: 5024991 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7829. Min Range: -8.7829
Max Act: 8.2204. Min Act: -0.1700
Data Index: 4189794 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7829. Min Range: -8.7829
Max Act: 8.0954. Min Act: -0.1700
Data Index: 6474785 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7829. Min Range: -8.7829
Max Act: 8.2204. Min Act: -0.1700
Data Index: 5905808 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7829. Min Range: -8.7829
Max Act: 8.1579. Min Act: -0.1700
Data Index: 2647086 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7829. Min Range: -8.7829
Max Act: 8.0954. Min Act: -0.1700
Data Index: 4905798 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7829. Min Range: -8.7829
Max Act: 8.0954. Min Act: -0.1700
Data Index: 97977 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7829. Min Range: -8.7829
Max Act: 8.0329. Min Act: -0.1700
Data Index: 4787620 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7829. Min Range: -8.7829
Max Act: 8.0329. Min Act: -0.1700
Data Index: 7523756 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7829. Min Range: -8.7829
Max Act: 8.0329. Min Act: -0.1700
Data Index: 8234881 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7829. Min Range: -8.7829
Max Act: 7.9079. Min Act: -0.1700
Data Index: 2291943 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7829. Min Range: -8.7829
Max Act: 7.9704. Min Act: -0.1700
Data Index: 3593948 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #19