Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4911 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0518. Min Range: -8.0518
Max Act: 8.0518. Min Act: -0.1700
Data Index: 7505963 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0518. Min Range: -8.0518
Max Act: 8.0206. Min Act: -0.1700
Data Index: 5330924 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0518. Min Range: -8.0518
Max Act: 7.8643. Min Act: -0.1700
Data Index: 4102773 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0518. Min Range: -8.0518
Max Act: 7.8643. Min Act: -0.1700
Data Index: 8102100 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0518. Min Range: -8.0518
Max Act: 7.8331. Min Act: -0.1700
Data Index: 1628546 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0518. Min Range: -8.0518
Max Act: 7.7706. Min Act: -0.1700
Data Index: 3205773 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0518. Min Range: -8.0518
Max Act: 7.7081. Min Act: -0.1700
Data Index: 8120034 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0518. Min Range: -8.0518
Max Act: 7.5206. Min Act: -0.1700
Data Index: 7211749 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0518. Min Range: -8.0518
Max Act: 7.5206. Min Act: -0.1700
Data Index: 8796496 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0518. Min Range: -8.0518
Max Act: 7.5206. Min Act: -0.1700
Data Index: 6718077 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0518. Min Range: -8.0518
Max Act: 7.4893. Min Act: -0.1700
Data Index: 6765007 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0518. Min Range: -8.0518
Max Act: 7.4893. Min Act: -0.1700
Data Index: 3071029 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0518. Min Range: -8.0518
Max Act: 7.4893. Min Act: -0.1700
Data Index: 535752 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0518. Min Range: -8.0518
Max Act: 7.4581. Min Act: -0.1700
Data Index: 7043994 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0518. Min Range: -8.0518
Max Act: 7.4581. Min Act: -0.1700
Data Index: 2254987 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0518. Min Range: -8.0518
Max Act: 7.4581. Min Act: -0.1700
Data Index: 2843386 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0518. Min Range: -8.0518
Max Act: 7.4581. Min Act: -0.1700
Data Index: 112937 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0518. Min Range: -8.0518
Max Act: 7.4268. Min Act: -0.1700
Data Index: 6684877 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0518. Min Range: -8.0518
Max Act: 7.4268. Min Act: -0.1700
Data Index: 1162018 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0518. Min Range: -8.0518
Max Act: 7.3956. Min Act: -0.1700
Data Index: 2376792 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #19