Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6351 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5574. Min Range: -4.5574
Max Act: 4.5574. Min Act: -0.1700
Data Index: 7067639 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5574. Min Range: -4.5574
Max Act: 4.5262. Min Act: -0.1700
Data Index: 3904447 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5574. Min Range: -4.5574
Max Act: 4.4012. Min Act: -0.1700
Data Index: 242917 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5574. Min Range: -4.5574
Max Act: 4.4012. Min Act: -0.1700
Data Index: 40899 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5574. Min Range: -4.5574
Max Act: 4.3699. Min Act: -0.1700
Data Index: 7709962 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5574. Min Range: -4.5574
Max Act: 4.3699. Min Act: -0.1700
Data Index: 3440001 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5574. Min Range: -4.5574
Max Act: 4.3387. Min Act: -0.1700
Data Index: 4789606 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5574. Min Range: -4.5574
Max Act: 4.3387. Min Act: -0.1700
Data Index: 6626256 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5574. Min Range: -4.5574
Max Act: 4.3387. Min Act: -0.1700
Data Index: 4951107 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5574. Min Range: -4.5574
Max Act: 4.3387. Min Act: -0.1700
Data Index: 5104641 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5574. Min Range: -4.5574
Max Act: 4.3387. Min Act: -0.1700
Data Index: 967333 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5574. Min Range: -4.5574
Max Act: 4.3387. Min Act: -0.1700
Data Index: 1140570 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5574. Min Range: -4.5574
Max Act: 4.3387. Min Act: -0.1700
Data Index: 8815300 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5574. Min Range: -4.5574
Max Act: 4.2762. Min Act: -0.1700
Data Index: 5845964 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5574. Min Range: -4.5574
Max Act: 4.2762. Min Act: -0.1700
Data Index: 8578352 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5574. Min Range: -4.5574
Max Act: 4.2762. Min Act: -0.1700
Data Index: 2976138 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5574. Min Range: -4.5574
Max Act: 4.2762. Min Act: -0.1700
Data Index: 8350339 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5574. Min Range: -4.5574
Max Act: 4.2449. Min Act: -0.1700
Data Index: 2008274 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5574. Min Range: -4.5574
Max Act: 4.2449. Min Act: -0.1700
Data Index: 363935 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5574. Min Range: -4.5574
Max Act: 4.2449. Min Act: -0.1700
Data Index: 8131649 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #19