Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 263 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6513. Min Range: -6.6513
Max Act: 6.6513. Min Act: -0.1700
Data Index: 1312310 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6513. Min Range: -6.6513
Max Act: 6.6513. Min Act: -0.1700
Data Index: 3242058 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6513. Min Range: -6.6513
Max Act: 6.6200. Min Act: -0.1700
Data Index: 3136087 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6513. Min Range: -6.6513
Max Act: 6.6200. Min Act: -0.1700
Data Index: 2085732 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6513. Min Range: -6.6513
Max Act: 6.6200. Min Act: -0.1700
Data Index: 7506247 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6513. Min Range: -6.6513
Max Act: 6.5888. Min Act: -0.1700
Data Index: 2131589 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6513. Min Range: -6.6513
Max Act: 6.5263. Min Act: -0.1700
Data Index: 2414475 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6513. Min Range: -6.6513
Max Act: 6.4950. Min Act: -0.1700
Data Index: 651682 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6513. Min Range: -6.6513
Max Act: 6.4950. Min Act: -0.1700
Data Index: 38895 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6513. Min Range: -6.6513
Max Act: 6.4638. Min Act: -0.1700
Data Index: 1030533 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6513. Min Range: -6.6513
Max Act: 6.4638. Min Act: -0.1700
Data Index: 1561410 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6513. Min Range: -6.6513
Max Act: 6.4638. Min Act: -0.1700
Data Index: 1211530 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6513. Min Range: -6.6513
Max Act: 6.4638. Min Act: -0.1700
Data Index: 3203891 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6513. Min Range: -6.6513
Max Act: 6.4325. Min Act: -0.1700
Data Index: 1122771 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6513. Min Range: -6.6513
Max Act: 6.4013. Min Act: -0.1700
Data Index: 5028940 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6513. Min Range: -6.6513
Max Act: 6.3700. Min Act: -0.1700
Data Index: 10135 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6513. Min Range: -6.6513
Max Act: 6.3700. Min Act: -0.1700
Data Index: 3319558 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6513. Min Range: -6.6513
Max Act: 6.3700. Min Act: -0.1700
Data Index: 1228880 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6513. Min Range: -6.6513
Max Act: 6.3700. Min Act: -0.1700
Data Index: 6863403 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6513. Min Range: -6.6513
Max Act: 6.3700. Min Act: -0.1700
Data Index: 311078 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #19