Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5819 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5141. Min Range: -4.5141
Max Act: 4.5141. Min Act: -0.1700
Data Index: 4551052 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5141. Min Range: -4.5141
Max Act: 4.5141. Min Act: -0.1700
Data Index: 8460317 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5141. Min Range: -4.5141
Max Act: 4.4829. Min Act: -0.1700
Data Index: 2481876 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5141. Min Range: -4.5141
Max Act: 4.4516. Min Act: -0.1700
Data Index: 1448269 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5141. Min Range: -4.5141
Max Act: 4.4516. Min Act: -0.1700
Data Index: 7245498 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5141. Min Range: -4.5141
Max Act: 4.3891. Min Act: -0.1700
Data Index: 7342383 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5141. Min Range: -4.5141
Max Act: 4.3891. Min Act: -0.1700
Data Index: 6950700 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5141. Min Range: -4.5141
Max Act: 4.3891. Min Act: -0.1700
Data Index: 7728135 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5141. Min Range: -4.5141
Max Act: 4.3579. Min Act: -0.1700
Data Index: 3747380 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5141. Min Range: -4.5141
Max Act: 4.3579. Min Act: -0.1700
Data Index: 2959054 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5141. Min Range: -4.5141
Max Act: 4.3579. Min Act: -0.1700
Data Index: 2895490 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5141. Min Range: -4.5141
Max Act: 4.3266. Min Act: -0.1700
Data Index: 6607898 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5141. Min Range: -4.5141
Max Act: 4.3266. Min Act: -0.1700
Data Index: 38466 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5141. Min Range: -4.5141
Max Act: 4.3579. Min Act: -0.1700
Data Index: 471489 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5141. Min Range: -4.5141
Max Act: 4.3266. Min Act: -0.1700
Data Index: 4919281 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5141. Min Range: -4.5141
Max Act: 4.3266. Min Act: -0.1700
Data Index: 5456826 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5141. Min Range: -4.5141
Max Act: 4.2954. Min Act: -0.1700
Data Index: 6655405 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5141. Min Range: -4.5141
Max Act: 4.2954. Min Act: -0.1700
Data Index: 7045536 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5141. Min Range: -4.5141
Max Act: 4.2954. Min Act: -0.1700
Data Index: 3848959 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5141. Min Range: -4.5141
Max Act: 4.2954. Min Act: -0.1700
Data Index: 7076502 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #19