Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3422 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6634. Min Range: -7.6634
Max Act: 7.6634. Min Act: -0.1700
Data Index: 7230767 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6634. Min Range: -7.6634
Max Act: 7.6634. Min Act: -0.1700
Data Index: 4032591 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6634. Min Range: -7.6634
Max Act: 7.6009. Min Act: -0.1700
Data Index: 7053411 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6634. Min Range: -7.6634
Max Act: 7.6634. Min Act: -0.1700
Data Index: 1040795 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6634. Min Range: -7.6634
Max Act: 7.6634. Min Act: -0.1700
Data Index: 2186161 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6634. Min Range: -7.6634
Max Act: 7.6009. Min Act: -0.1700
Data Index: 5885805 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6634. Min Range: -7.6634
Max Act: 7.6009. Min Act: -0.1700
Data Index: 667853 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6634. Min Range: -7.6634
Max Act: 7.6009. Min Act: -0.1700
Data Index: 2590801 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6634. Min Range: -7.6634
Max Act: 7.6634. Min Act: -0.1700
Data Index: 2484216 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6634. Min Range: -7.6634
Max Act: 7.6009. Min Act: -0.1700
Data Index: 2037325 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6634. Min Range: -7.6634
Max Act: 7.5384. Min Act: -0.1700
Data Index: 1517824 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6634. Min Range: -7.6634
Max Act: 7.5384. Min Act: -0.1700
Data Index: 5559743 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6634. Min Range: -7.6634
Max Act: 7.5384. Min Act: -0.1700
Data Index: 598490 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6634. Min Range: -7.6634
Max Act: 7.5384. Min Act: -0.1700
Data Index: 1633887 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6634. Min Range: -7.6634
Max Act: 7.5384. Min Act: -0.1700
Data Index: 6396879 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6634. Min Range: -7.6634
Max Act: 7.5384. Min Act: -0.1700
Data Index: 5331025 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6634. Min Range: -7.6634
Max Act: 7.5384. Min Act: -0.1700
Data Index: 6452835 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6634. Min Range: -7.6634
Max Act: 7.5384. Min Act: -0.1700
Data Index: 4099103 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6634. Min Range: -7.6634
Max Act: 7.5384. Min Act: -0.1700
Data Index: 3361357 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6634. Min Range: -7.6634
Max Act: 7.5384. Min Act: -0.1700
Data Index: 3356508 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #19