Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3189 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3066. Min Range: -6.3066
Max Act: 6.3066. Min Act: -0.1700
Data Index: 7973085 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3066. Min Range: -6.3066
Max Act: 6.0566. Min Act: -0.1700
Data Index: 1865494 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3066. Min Range: -6.3066
Max Act: 5.9316. Min Act: -0.1700
Data Index: 4768063 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3066. Min Range: -6.3066
Max Act: 5.9003. Min Act: -0.1700
Data Index: 6665256 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3066. Min Range: -6.3066
Max Act: 5.9003. Min Act: -0.1700
Data Index: 696546 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3066. Min Range: -6.3066
Max Act: 5.9003. Min Act: -0.1700
Data Index: 5459609 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3066. Min Range: -6.3066
Max Act: 5.8378. Min Act: -0.1700
Data Index: 3663279 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3066. Min Range: -6.3066
Max Act: 5.8066. Min Act: -0.1700
Data Index: 1044186 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3066. Min Range: -6.3066
Max Act: 5.8066. Min Act: -0.1700
Data Index: 5898959 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3066. Min Range: -6.3066
Max Act: 5.7753. Min Act: -0.1700
Data Index: 5038958 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3066. Min Range: -6.3066
Max Act: 5.7128. Min Act: -0.1700
Data Index: 4413433 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3066. Min Range: -6.3066
Max Act: 5.7128. Min Act: -0.1700
Data Index: 8123148 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3066. Min Range: -6.3066
Max Act: 5.6816. Min Act: -0.1700
Data Index: 4921263 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3066. Min Range: -6.3066
Max Act: 5.7128. Min Act: -0.1700
Data Index: 436946 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3066. Min Range: -6.3066
Max Act: 5.7128. Min Act: -0.1700
Data Index: 6095378 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3066. Min Range: -6.3066
Max Act: 5.6816. Min Act: -0.1700
Data Index: 2147624 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3066. Min Range: -6.3066
Max Act: 5.6503. Min Act: -0.1700
Data Index: 1391612 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3066. Min Range: -6.3066
Max Act: 5.6503. Min Act: -0.1700
Data Index: 2545000 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3066. Min Range: -6.3066
Max Act: 5.6191. Min Act: -0.1700
Data Index: 7356888 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3066. Min Range: -6.3066
Max Act: 5.6191. Min Act: -0.1700
Data Index: 661280 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #19