Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4539 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4756. Min Range: -7.4756
Max Act: 7.4756. Min Act: -0.1700
Data Index: 387102 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4756. Min Range: -7.4756
Max Act: 7.0381. Min Act: -0.1700
Data Index: 586127 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4756. Min Range: -7.4756
Max Act: 7.0381. Min Act: -0.1700
Data Index: 730222 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4756. Min Range: -7.4756
Max Act: 7.0381. Min Act: -0.1700
Data Index: 2000040 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4756. Min Range: -7.4756
Max Act: 6.9443. Min Act: -0.1700
Data Index: 5009829 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4756. Min Range: -7.4756
Max Act: 6.9131. Min Act: -0.1700
Data Index: 3465578 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4756. Min Range: -7.4756
Max Act: 6.8818. Min Act: -0.1700
Data Index: 1996306 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4756. Min Range: -7.4756
Max Act: 6.8506. Min Act: -0.1700
Data Index: 2292934 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4756. Min Range: -7.4756
Max Act: 6.8193. Min Act: -0.1700
Data Index: 7386705 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4756. Min Range: -7.4756
Max Act: 6.8193. Min Act: -0.1700
Data Index: 3680518 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4756. Min Range: -7.4756
Max Act: 6.8506. Min Act: -0.1700
Data Index: 2124789 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4756. Min Range: -7.4756
Max Act: 6.7256. Min Act: -0.1700
Data Index: 7185061 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4756. Min Range: -7.4756
Max Act: 6.6943. Min Act: -0.1700
Data Index: 5908729 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4756. Min Range: -7.4756
Max Act: 6.6631. Min Act: -0.1700
Data Index: 3252143 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4756. Min Range: -7.4756
Max Act: 6.6318. Min Act: -0.1700
Data Index: 1326494 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4756. Min Range: -7.4756
Max Act: 6.6318. Min Act: -0.1700
Data Index: 3446706 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4756. Min Range: -7.4756
Max Act: 6.5693. Min Act: -0.1700
Data Index: 5415684 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4756. Min Range: -7.4756
Max Act: 6.6006. Min Act: -0.1700
Data Index: 4215727 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4756. Min Range: -7.4756
Max Act: 6.5693. Min Act: -0.1700
Data Index: 248517 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4756. Min Range: -7.4756
Max Act: 6.5693. Min Act: -0.1700
Data Index: 6070612 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #19