Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2591 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5947. Min Range: -4.5947
Max Act: 4.5947. Min Act: -0.1700
Data Index: 4096214 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5947. Min Range: -4.5947
Max Act: 4.5947. Min Act: -0.1700
Data Index: 4096216 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5947. Min Range: -4.5947
Max Act: 4.5635. Min Act: -0.1700
Data Index: 4096219 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5947. Min Range: -4.5947
Max Act: 4.5010. Min Act: -0.1700
Data Index: 8000871 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5947. Min Range: -4.5947
Max Act: 4.4697. Min Act: -0.1700
Data Index: 1438227 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5947. Min Range: -4.5947
Max Act: 4.4072. Min Act: -0.1700
Data Index: 7930479 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5947. Min Range: -4.5947
Max Act: 4.4072. Min Act: -0.1700
Data Index: 1029211 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5947. Min Range: -4.5947
Max Act: 4.4072. Min Act: -0.1700
Data Index: 3817462 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5947. Min Range: -4.5947
Max Act: 4.4072. Min Act: -0.1700
Data Index: 4503843 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5947. Min Range: -4.5947
Max Act: 4.4072. Min Act: -0.1700
Data Index: 6888438 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5947. Min Range: -4.5947
Max Act: 4.3447. Min Act: -0.1700
Data Index: 4669578 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5947. Min Range: -4.5947
Max Act: 4.3447. Min Act: -0.1700
Data Index: 800044 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5947. Min Range: -4.5947
Max Act: 4.3135. Min Act: -0.1700
Data Index: 5291784 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5947. Min Range: -4.5947
Max Act: 4.3135. Min Act: -0.1700
Data Index: 6616374 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5947. Min Range: -4.5947
Max Act: 4.3135. Min Act: -0.1700
Data Index: 3091611 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5947. Min Range: -4.5947
Max Act: 4.2822. Min Act: -0.1700
Data Index: 6986880 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5947. Min Range: -4.5947
Max Act: 4.2822. Min Act: -0.1700
Data Index: 4044261 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5947. Min Range: -4.5947
Max Act: 4.2822. Min Act: -0.1700
Data Index: 7050856 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5947. Min Range: -4.5947
Max Act: 4.2822. Min Act: -0.1700
Data Index: 1166191 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5947. Min Range: -4.5947
Max Act: 4.2822. Min Act: -0.1700
Data Index: 3617261 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #19