Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 509 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9917. Min Range: -8.9917
Max Act: 8.9917. Min Act: -0.1700
Data Index: 4959694 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9917. Min Range: -8.9917
Max Act: 8.8042. Min Act: -0.1700
Data Index: 3434105 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9917. Min Range: -8.9917
Max Act: 8.7417. Min Act: -0.1700
Data Index: 1009593 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9917. Min Range: -8.9917
Max Act: 8.3042. Min Act: -0.1700
Data Index: 2108161 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9917. Min Range: -8.9917
Max Act: 8.3042. Min Act: -0.1700
Data Index: 2947754 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9917. Min Range: -8.9917
Max Act: 8.1479. Min Act: -0.1700
Data Index: 6281592 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9917. Min Range: -8.9917
Max Act: 8.1479. Min Act: -0.1700
Data Index: 1021899 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9917. Min Range: -8.9917
Max Act: 8.0229. Min Act: -0.1700
Data Index: 3209548 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9917. Min Range: -8.9917
Max Act: 7.9292. Min Act: -0.1700
Data Index: 1705549 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9917. Min Range: -8.9917
Max Act: 7.8354. Min Act: -0.1700
Data Index: 8748518 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9917. Min Range: -8.9917
Max Act: 7.8667. Min Act: -0.1700
Data Index: 5304925 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9917. Min Range: -8.9917
Max Act: 7.8042. Min Act: -0.1700
Data Index: 172955 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9917. Min Range: -8.9917
Max Act: 7.8042. Min Act: -0.1700
Data Index: 2081211 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9917. Min Range: -8.9917
Max Act: 7.8042. Min Act: -0.1700
Data Index: 70904 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9917. Min Range: -8.9917
Max Act: 7.8042. Min Act: -0.1700
Data Index: 1367602 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9917. Min Range: -8.9917
Max Act: 7.8042. Min Act: -0.1700
Data Index: 1909922 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9917. Min Range: -8.9917
Max Act: 7.8042. Min Act: -0.1700
Data Index: 1955997 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9917. Min Range: -8.9917
Max Act: 7.8042. Min Act: -0.1700
Data Index: 6947702 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9917. Min Range: -8.9917
Max Act: 7.8042. Min Act: -0.1700
Data Index: 3870121 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9917. Min Range: -8.9917
Max Act: 7.7729. Min Act: -0.1700
Data Index: 6633112 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #19