Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3787 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9628. Min Range: -5.9628
Max Act: 5.9628. Min Act: -0.1700
Data Index: 8365312 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9628. Min Range: -5.9628
Max Act: 5.9003. Min Act: -0.1700
Data Index: 8365320 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9628. Min Range: -5.9628
Max Act: 5.9316. Min Act: -0.1700
Data Index: 2283094 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9628. Min Range: -5.9628
Max Act: 5.9003. Min Act: -0.1700
Data Index: 2283086 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9628. Min Range: -5.9628
Max Act: 5.9003. Min Act: -0.1700
Data Index: 3272557 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9628. Min Range: -5.9628
Max Act: 5.9003. Min Act: -0.1700
Data Index: 5837059 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9628. Min Range: -5.9628
Max Act: 5.8378. Min Act: -0.1700
Data Index: 7694994 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9628. Min Range: -5.9628
Max Act: 5.8066. Min Act: -0.1700
Data Index: 278294 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9628. Min Range: -5.9628
Max Act: 5.8066. Min Act: -0.1700
Data Index: 5557634 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9628. Min Range: -5.9628
Max Act: 5.8066. Min Act: -0.1700
Data Index: 7854518 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9628. Min Range: -5.9628
Max Act: 5.7441. Min Act: -0.1700
Data Index: 5557633 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9628. Min Range: -5.9628
Max Act: 5.7753. Min Act: -0.1700
Data Index: 5002427 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9628. Min Range: -5.9628
Max Act: 5.7753. Min Act: -0.1700
Data Index: 4821462 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9628. Min Range: -5.9628
Max Act: 5.7753. Min Act: -0.1700
Data Index: 5557629 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9628. Min Range: -5.9628
Max Act: 5.7753. Min Act: -0.1700
Data Index: 5557630 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9628. Min Range: -5.9628
Max Act: 5.7753. Min Act: -0.1700
Data Index: 3918001 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9628. Min Range: -5.9628
Max Act: 5.7441. Min Act: -0.1700
Data Index: 4781663 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9628. Min Range: -5.9628
Max Act: 5.7753. Min Act: -0.1700
Data Index: 5557628 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9628. Min Range: -5.9628
Max Act: 5.7441. Min Act: -0.1700
Data Index: 6143058 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9628. Min Range: -5.9628
Max Act: 5.7441. Min Act: -0.1700
Data Index: 5557631 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #19