Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1068 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1262. Min Range: -5.1262
Max Act: 5.1262. Min Act: -0.1700
Data Index: 3004551 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1262. Min Range: -5.1262
Max Act: 5.0637. Min Act: -0.1700
Data Index: 5919800 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1262. Min Range: -5.1262
Max Act: 4.9700. Min Act: -0.1700
Data Index: 2359839 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1262. Min Range: -5.1262
Max Act: 4.9700. Min Act: -0.1700
Data Index: 1200952 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1262. Min Range: -5.1262
Max Act: 4.9075. Min Act: -0.1700
Data Index: 6936930 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1262. Min Range: -5.1262
Max Act: 4.9075. Min Act: -0.1700
Data Index: 5049462 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1262. Min Range: -5.1262
Max Act: 4.8762. Min Act: -0.1700
Data Index: 8636719 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1262. Min Range: -5.1262
Max Act: 4.8762. Min Act: -0.1700
Data Index: 4672156 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1262. Min Range: -5.1262
Max Act: 4.8762. Min Act: -0.1700
Data Index: 4320915 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1262. Min Range: -5.1262
Max Act: 4.8450. Min Act: -0.1700
Data Index: 387587 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1262. Min Range: -5.1262
Max Act: 4.8137. Min Act: -0.1700
Data Index: 5460715 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1262. Min Range: -5.1262
Max Act: 4.8137. Min Act: -0.1700
Data Index: 4180777 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1262. Min Range: -5.1262
Max Act: 4.8137. Min Act: -0.1700
Data Index: 6644985 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1262. Min Range: -5.1262
Max Act: 4.7825. Min Act: -0.1700
Data Index: 1545681 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1262. Min Range: -5.1262
Max Act: 4.7825. Min Act: -0.1700
Data Index: 7401321 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1262. Min Range: -5.1262
Max Act: 4.7512. Min Act: -0.1700
Data Index: 6294783 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1262. Min Range: -5.1262
Max Act: 4.7825. Min Act: -0.1700
Data Index: 7684589 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1262. Min Range: -5.1262
Max Act: 4.7512. Min Act: -0.1700
Data Index: 12201 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1262. Min Range: -5.1262
Max Act: 4.7512. Min Act: -0.1700
Data Index: 2763258 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1262. Min Range: -5.1262
Max Act: 4.7512. Min Act: -0.1700
Data Index: 7541529 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #19