Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4648 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5747. Min Range: -6.5747
Max Act: 6.5747. Min Act: -0.1700
Data Index: 7685641 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5747. Min Range: -6.5747
Max Act: 6.5747. Min Act: -0.1700
Data Index: 3955452 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5747. Min Range: -6.5747
Max Act: 6.4809. Min Act: -0.1700
Data Index: 1847399 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5747. Min Range: -6.5747
Max Act: 6.4497. Min Act: -0.1700
Data Index: 7677449 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5747. Min Range: -6.5747
Max Act: 6.3559. Min Act: -0.1700
Data Index: 6576851 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5747. Min Range: -6.5747
Max Act: 6.3559. Min Act: -0.1700
Data Index: 3955448 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5747. Min Range: -6.5747
Max Act: 6.2934. Min Act: -0.1700
Data Index: 1770170 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5747. Min Range: -6.5747
Max Act: 6.2622. Min Act: -0.1700
Data Index: 5949603 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5747. Min Range: -6.5747
Max Act: 6.2622. Min Act: -0.1700
Data Index: 4069531 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5747. Min Range: -6.5747
Max Act: 6.2309. Min Act: -0.1700
Data Index: 4526535 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5747. Min Range: -6.5747
Max Act: 6.1997. Min Act: -0.1700
Data Index: 5315937 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5747. Min Range: -6.5747
Max Act: 6.1372. Min Act: -0.1700
Data Index: 3292120 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5747. Min Range: -6.5747
Max Act: 6.1372. Min Act: -0.1700
Data Index: 3955449 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5747. Min Range: -6.5747
Max Act: 6.1059. Min Act: -0.1700
Data Index: 6326867 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5747. Min Range: -6.5747
Max Act: 6.0747. Min Act: -0.1700
Data Index: 5749256 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5747. Min Range: -6.5747
Max Act: 6.1059. Min Act: -0.1700
Data Index: 5806442 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5747. Min Range: -6.5747
Max Act: 6.0434. Min Act: -0.1700
Data Index: 3484949 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5747. Min Range: -6.5747
Max Act: 6.0747. Min Act: -0.1700
Data Index: 3406091 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5747. Min Range: -6.5747
Max Act: 6.0122. Min Act: -0.1700
Data Index: 2808111 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5747. Min Range: -6.5747
Max Act: 6.0122. Min Act: -0.1700
Data Index: 6105966 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #19