Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1851 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6467. Min Range: -8.6467
Max Act: 8.6467. Min Act: -0.1700
Data Index: 856790 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6467. Min Range: -8.6467
Max Act: 8.4592. Min Act: -0.1700
Data Index: 6319823 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6467. Min Range: -8.6467
Max Act: 8.2092. Min Act: -0.1700
Data Index: 645799 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6467. Min Range: -8.6467
Max Act: 8.2092. Min Act: -0.1700
Data Index: 1268331 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6467. Min Range: -8.6467
Max Act: 8.2092. Min Act: -0.1700
Data Index: 2170837 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6467. Min Range: -8.6467
Max Act: 8.2092. Min Act: -0.1700
Data Index: 843096 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6467. Min Range: -8.6467
Max Act: 8.2092. Min Act: -0.1700
Data Index: 852402 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6467. Min Range: -8.6467
Max Act: 8.1467. Min Act: -0.1700
Data Index: 998685 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6467. Min Range: -8.6467
Max Act: 8.0217. Min Act: -0.1700
Data Index: 241949 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6467. Min Range: -8.6467
Max Act: 7.9592. Min Act: -0.1700
Data Index: 3711573 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6467. Min Range: -8.6467
Max Act: 7.9592. Min Act: -0.1700
Data Index: 2842954 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6467. Min Range: -8.6467
Max Act: 7.8342. Min Act: -0.1700
Data Index: 7909156 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6467. Min Range: -8.6467
Max Act: 7.8967. Min Act: -0.1700
Data Index: 8181827 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6467. Min Range: -8.6467
Max Act: 7.8342. Min Act: -0.1700
Data Index: 4110015 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6467. Min Range: -8.6467
Max Act: 7.8342. Min Act: -0.1700
Data Index: 7463869 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6467. Min Range: -8.6467
Max Act: 7.8342. Min Act: -0.1700
Data Index: 6824267 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6467. Min Range: -8.6467
Max Act: 7.8342. Min Act: -0.1700
Data Index: 5032486 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6467. Min Range: -8.6467
Max Act: 7.7717. Min Act: -0.1700
Data Index: 4988046 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6467. Min Range: -8.6467
Max Act: 7.7717. Min Act: -0.1700
Data Index: 7985008 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6467. Min Range: -8.6467
Max Act: 7.7717. Min Act: -0.1700
Data Index: 6535427 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #19