Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5059 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7606. Min Range: -7.7606
Max Act: 7.7606. Min Act: -0.1700
Data Index: 7247821 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7606. Min Range: -7.7606
Max Act: 7.5731. Min Act: -0.1700
Data Index: 4966766 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7606. Min Range: -7.7606
Max Act: 7.2918. Min Act: -0.1700
Data Index: 6008758 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7606. Min Range: -7.7606
Max Act: 7.2606. Min Act: -0.1700
Data Index: 2328765 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7606. Min Range: -7.7606
Max Act: 7.2918. Min Act: -0.1700
Data Index: 7873274 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7606. Min Range: -7.7606
Max Act: 7.2606. Min Act: -0.1700
Data Index: 6864096 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7606. Min Range: -7.7606
Max Act: 7.2293. Min Act: -0.1700
Data Index: 3655249 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7606. Min Range: -7.7606
Max Act: 7.2606. Min Act: -0.1700
Data Index: 6060911 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7606. Min Range: -7.7606
Max Act: 7.2606. Min Act: -0.1700
Data Index: 968864 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7606. Min Range: -7.7606
Max Act: 7.2293. Min Act: -0.1700
Data Index: 3676745 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7606. Min Range: -7.7606
Max Act: 7.1668. Min Act: -0.1700
Data Index: 5775774 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7606. Min Range: -7.7606
Max Act: 7.1356. Min Act: -0.1700
Data Index: 2417163 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7606. Min Range: -7.7606
Max Act: 7.1668. Min Act: -0.1700
Data Index: 2256980 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7606. Min Range: -7.7606
Max Act: 7.1668. Min Act: -0.1700
Data Index: 1077550 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7606. Min Range: -7.7606
Max Act: 7.1043. Min Act: -0.1700
Data Index: 7894370 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7606. Min Range: -7.7606
Max Act: 7.1356. Min Act: -0.1700
Data Index: 1773949 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7606. Min Range: -7.7606
Max Act: 7.0731. Min Act: -0.1700
Data Index: 7974520 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7606. Min Range: -7.7606
Max Act: 7.0731. Min Act: -0.1700
Data Index: 5500582 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7606. Min Range: -7.7606
Max Act: 7.0418. Min Act: -0.1700
Data Index: 6238716 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7606. Min Range: -7.7606
Max Act: 7.0418. Min Act: -0.1700
Data Index: 4916798 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #19