Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4416 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4262. Min Range: -6.4262
Max Act: 6.3950. Min Act: -0.1700
Data Index: 6064977 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4262. Min Range: -6.4262
Max Act: 6.4262. Min Act: -0.1700
Data Index: 2191729 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4262. Min Range: -6.4262
Max Act: 6.4262. Min Act: -0.1700
Data Index: 2191730 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4262. Min Range: -6.4262
Max Act: 6.3325. Min Act: -0.1700
Data Index: 523143 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4262. Min Range: -6.4262
Max Act: 6.2700. Min Act: -0.1700
Data Index: 6485837 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4262. Min Range: -6.4262
Max Act: 6.2700. Min Act: -0.1700
Data Index: 4403673 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4262. Min Range: -6.4262
Max Act: 6.2387. Min Act: -0.1700
Data Index: 6601088 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4262. Min Range: -6.4262
Max Act: 6.2075. Min Act: -0.1700
Data Index: 7954410 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4262. Min Range: -6.4262
Max Act: 6.2075. Min Act: -0.1700
Data Index: 6474225 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4262. Min Range: -6.4262
Max Act: 6.1762. Min Act: -0.1700
Data Index: 4403667 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4262. Min Range: -6.4262
Max Act: 6.2075. Min Act: -0.1700
Data Index: 7805127 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4262. Min Range: -6.4262
Max Act: 6.2075. Min Act: -0.1700
Data Index: 349273 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4262. Min Range: -6.4262
Max Act: 6.1762. Min Act: -0.1700
Data Index: 4971964 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4262. Min Range: -6.4262
Max Act: 6.1450. Min Act: -0.1700
Data Index: 556528 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4262. Min Range: -6.4262
Max Act: 6.1450. Min Act: -0.1700
Data Index: 307057 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4262. Min Range: -6.4262
Max Act: 6.1450. Min Act: -0.1700
Data Index: 6601086 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4262. Min Range: -6.4262
Max Act: 6.1137. Min Act: -0.1700
Data Index: 6485839 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4262. Min Range: -6.4262
Max Act: 6.1137. Min Act: -0.1700
Data Index: 2455141 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4262. Min Range: -6.4262
Max Act: 6.0512. Min Act: -0.1700
Data Index: 2520515 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4262. Min Range: -6.4262
Max Act: 6.0825. Min Act: -0.1700
Data Index: 2331777 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19