Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3405 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2480. Min Range: -4.2480
Max Act: 4.2480. Min Act: -0.1700
Data Index: 5611313 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2480. Min Range: -4.2480
Max Act: 4.1543. Min Act: -0.1700
Data Index: 6929786 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2480. Min Range: -4.2480
Max Act: 4.1543. Min Act: -0.1700
Data Index: 1326290 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2480. Min Range: -4.2480
Max Act: 4.0292. Min Act: -0.1700
Data Index: 7858729 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2480. Min Range: -4.2480
Max Act: 3.9980. Min Act: -0.1700
Data Index: 3218741 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2480. Min Range: -4.2480
Max Act: 3.9354. Min Act: -0.1700
Data Index: 4550941 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2480. Min Range: -4.2480
Max Act: 3.9354. Min Act: -0.1700
Data Index: 284406 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2480. Min Range: -4.2480
Max Act: 3.9354. Min Act: -0.1700
Data Index: 2250433 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2480. Min Range: -4.2480
Max Act: 3.9354. Min Act: -0.1700
Data Index: 165661 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2480. Min Range: -4.2480
Max Act: 3.9042. Min Act: -0.1700
Data Index: 5863330 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2480. Min Range: -4.2480
Max Act: 3.9042. Min Act: -0.1700
Data Index: 996948 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2480. Min Range: -4.2480
Max Act: 3.8729. Min Act: -0.1700
Data Index: 1606345 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2480. Min Range: -4.2480
Max Act: 3.8104. Min Act: -0.1700
Data Index: 3885396 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2480. Min Range: -4.2480
Max Act: 3.8104. Min Act: -0.1700
Data Index: 2011205 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2480. Min Range: -4.2480
Max Act: 3.8104. Min Act: -0.1700
Data Index: 1050336 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2480. Min Range: -4.2480
Max Act: 3.7791. Min Act: -0.1700
Data Index: 1713156 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2480. Min Range: -4.2480
Max Act: 3.7791. Min Act: -0.1700
Data Index: 3930034 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2480. Min Range: -4.2480
Max Act: 3.7791. Min Act: -0.1700
Data Index: 4931198 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2480. Min Range: -4.2480
Max Act: 3.7791. Min Act: -0.1700
Data Index: 7167677 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2480. Min Range: -4.2480
Max Act: 3.7791. Min Act: -0.1700
Data Index: 1517393 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #19