Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2920 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0371. Min Range: -7.0371
Max Act: 7.0371. Min Act: -0.1700
Data Index: 3976193 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0371. Min Range: -7.0371
Max Act: 6.8183. Min Act: -0.1700
Data Index: 2102971 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0371. Min Range: -7.0371
Max Act: 6.7871. Min Act: -0.1700
Data Index: 4687625 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0371. Min Range: -7.0371
Max Act: 6.7871. Min Act: -0.1700
Data Index: 2479936 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0371. Min Range: -7.0371
Max Act: 6.7871. Min Act: -0.1700
Data Index: 7474721 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0371. Min Range: -7.0371
Max Act: 6.7246. Min Act: -0.1700
Data Index: 7698170 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0371. Min Range: -7.0371
Max Act: 6.6933. Min Act: -0.1700
Data Index: 8543709 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0371. Min Range: -7.0371
Max Act: 6.6933. Min Act: -0.1700
Data Index: 1577912 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0371. Min Range: -7.0371
Max Act: 6.6933. Min Act: -0.1700
Data Index: 500006 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0371. Min Range: -7.0371
Max Act: 6.5996. Min Act: -0.1700
Data Index: 981133 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0371. Min Range: -7.0371
Max Act: 6.5996. Min Act: -0.1700
Data Index: 8770772 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0371. Min Range: -7.0371
Max Act: 6.5683. Min Act: -0.1700
Data Index: 380859 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0371. Min Range: -7.0371
Max Act: 6.5371. Min Act: -0.1700
Data Index: 2783846 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0371. Min Range: -7.0371
Max Act: 6.5683. Min Act: -0.1700
Data Index: 2358059 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0371. Min Range: -7.0371
Max Act: 6.5371. Min Act: -0.1700
Data Index: 3083406 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0371. Min Range: -7.0371
Max Act: 6.5371. Min Act: -0.1700
Data Index: 4693714 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0371. Min Range: -7.0371
Max Act: 6.5058. Min Act: -0.1700
Data Index: 3358865 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0371. Min Range: -7.0371
Max Act: 6.4746. Min Act: -0.1700
Data Index: 6778961 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0371. Min Range: -7.0371
Max Act: 6.4746. Min Act: -0.1700
Data Index: 6528569 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0371. Min Range: -7.0371
Max Act: 6.4746. Min Act: -0.1700
Data Index: 3594464 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19