Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1908 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4329. Min Range: -8.4329
Max Act: 8.4329. Min Act: -0.1700
Data Index: 6579799 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4329. Min Range: -8.4329
Max Act: 8.1829. Min Act: -0.1700
Data Index: 963013 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4329. Min Range: -8.4329
Max Act: 8.0579. Min Act: -0.1700
Data Index: 7204552 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4329. Min Range: -8.4329
Max Act: 8.0579. Min Act: -0.1700
Data Index: 615495 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4329. Min Range: -8.4329
Max Act: 7.9954. Min Act: -0.1700
Data Index: 418 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4329. Min Range: -8.4329
Max Act: 7.9329. Min Act: -0.1700
Data Index: 963016 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4329. Min Range: -8.4329
Max Act: 7.9954. Min Act: -0.1700
Data Index: 7111741 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4329. Min Range: -8.4329
Max Act: 7.9329. Min Act: -0.1700
Data Index: 1696204 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4329. Min Range: -8.4329
Max Act: 7.7454. Min Act: -0.1700
Data Index: 5472735 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4329. Min Range: -8.4329
Max Act: 7.6829. Min Act: -0.1700
Data Index: 4325003 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4329. Min Range: -8.4329
Max Act: 7.6829. Min Act: -0.1700
Data Index: 2570805 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4329. Min Range: -8.4329
Max Act: 7.6829. Min Act: -0.1700
Data Index: 94798 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4329. Min Range: -8.4329
Max Act: 7.6829. Min Act: -0.1700
Data Index: 976805 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4329. Min Range: -8.4329
Max Act: 7.5891. Min Act: -0.1700
Data Index: 1254740 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4329. Min Range: -8.4329
Max Act: 7.5891. Min Act: -0.1700
Data Index: 7717017 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4329. Min Range: -8.4329
Max Act: 7.5891. Min Act: -0.1700
Data Index: 6554102 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4329. Min Range: -8.4329
Max Act: 7.5579. Min Act: -0.1700
Data Index: 5858614 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4329. Min Range: -8.4329
Max Act: 7.5579. Min Act: -0.1700
Data Index: 3253795 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4329. Min Range: -8.4329
Max Act: 7.5579. Min Act: -0.1700
Data Index: 963006 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4329. Min Range: -8.4329
Max Act: 7.5266. Min Act: -0.1700
Data Index: 6540239 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #19