Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3436 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1708. Min Range: -5.1708
Max Act: 5.1708. Min Act: -0.1700
Data Index: 7568900 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1708. Min Range: -5.1708
Max Act: 5.0770. Min Act: -0.1700
Data Index: 3751539 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1708. Min Range: -5.1708
Max Act: 5.0770. Min Act: -0.1700
Data Index: 6752104 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1708. Min Range: -5.1708
Max Act: 5.0145. Min Act: -0.1700
Data Index: 6276437 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1708. Min Range: -5.1708
Max Act: 4.9833. Min Act: -0.1700
Data Index: 6726946 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1708. Min Range: -5.1708
Max Act: 4.9520. Min Act: -0.1700
Data Index: 5493071 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1708. Min Range: -5.1708
Max Act: 4.9833. Min Act: -0.1700
Data Index: 1342305 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1708. Min Range: -5.1708
Max Act: 5.0145. Min Act: -0.1700
Data Index: 2406077 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1708. Min Range: -5.1708
Max Act: 4.9520. Min Act: -0.1700
Data Index: 7971713 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1708. Min Range: -5.1708
Max Act: 4.9520. Min Act: -0.1700
Data Index: 7770109 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1708. Min Range: -5.1708
Max Act: 4.9520. Min Act: -0.1700
Data Index: 1216811 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1708. Min Range: -5.1708
Max Act: 4.9208. Min Act: -0.1700
Data Index: 2561074 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1708. Min Range: -5.1708
Max Act: 4.9208. Min Act: -0.1700
Data Index: 3002704 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1708. Min Range: -5.1708
Max Act: 4.9208. Min Act: -0.1700
Data Index: 4593684 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1708. Min Range: -5.1708
Max Act: 4.9208. Min Act: -0.1700
Data Index: 8366300 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1708. Min Range: -5.1708
Max Act: 4.8895. Min Act: -0.1700
Data Index: 7000827 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1708. Min Range: -5.1708
Max Act: 4.8895. Min Act: -0.1700
Data Index: 2971759 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1708. Min Range: -5.1708
Max Act: 4.8895. Min Act: -0.1700
Data Index: 3561228 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1708. Min Range: -5.1708
Max Act: 4.8895. Min Act: -0.1700
Data Index: 6054566 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1708. Min Range: -5.1708
Max Act: 4.8895. Min Act: -0.1700
Data Index: 3760725 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #19