Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 445 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7786. Min Range: -6.7786
Max Act: 6.7786. Min Act: -0.1700
Data Index: 3347483 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7786. Min Range: -6.7786
Max Act: 6.7786. Min Act: -0.1700
Data Index: 6605605 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7786. Min Range: -6.7786
Max Act: 6.7474. Min Act: -0.1700
Data Index: 7568107 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7786. Min Range: -6.7786
Max Act: 6.6849. Min Act: -0.1700
Data Index: 6129836 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7786. Min Range: -6.7786
Max Act: 6.6849. Min Act: -0.1700
Data Index: 2840560 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7786. Min Range: -6.7786
Max Act: 6.6536. Min Act: -0.1700
Data Index: 7797425 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7786. Min Range: -6.7786
Max Act: 6.6536. Min Act: -0.1700
Data Index: 3231118 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7786. Min Range: -6.7786
Max Act: 6.6536. Min Act: -0.1700
Data Index: 6116773 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7786. Min Range: -6.7786
Max Act: 6.5911. Min Act: -0.1700
Data Index: 1333717 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7786. Min Range: -6.7786
Max Act: 6.6224. Min Act: -0.1700
Data Index: 3470383 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7786. Min Range: -6.7786
Max Act: 6.6224. Min Act: -0.1700
Data Index: 8327733 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7786. Min Range: -6.7786
Max Act: 6.5599. Min Act: -0.1700
Data Index: 5371618 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7786. Min Range: -6.7786
Max Act: 6.5286. Min Act: -0.1700
Data Index: 3150050 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7786. Min Range: -6.7786
Max Act: 6.5599. Min Act: -0.1700
Data Index: 6983020 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7786. Min Range: -6.7786
Max Act: 6.5286. Min Act: -0.1700
Data Index: 529695 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7786. Min Range: -6.7786
Max Act: 6.4974. Min Act: -0.1700
Data Index: 3965204 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7786. Min Range: -6.7786
Max Act: 6.4661. Min Act: -0.1700
Data Index: 658124 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7786. Min Range: -6.7786
Max Act: 6.4661. Min Act: -0.1700
Data Index: 2611243 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7786. Min Range: -6.7786
Max Act: 6.4974. Min Act: -0.1700
Data Index: 4527763 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7786. Min Range: -6.7786
Max Act: 6.4349. Min Act: -0.1700
Data Index: 1335200 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #19