Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1482 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4710. Min Range: -5.4710
Max Act: 5.4710. Min Act: -0.1700
Data Index: 4972896 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4710. Min Range: -5.4710
Max Act: 5.2210. Min Act: -0.1700
Data Index: 6434655 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4710. Min Range: -5.4710
Max Act: 5.1898. Min Act: -0.1700
Data Index: 2259094 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4710. Min Range: -5.4710
Max Act: 5.1273. Min Act: -0.1700
Data Index: 7339971 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4710. Min Range: -5.4710
Max Act: 5.1585. Min Act: -0.1700
Data Index: 1235563 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4710. Min Range: -5.4710
Max Act: 5.1273. Min Act: -0.1700
Data Index: 4254905 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4710. Min Range: -5.4710
Max Act: 5.1585. Min Act: -0.1700
Data Index: 7423977 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4710. Min Range: -5.4710
Max Act: 5.0648. Min Act: -0.1700
Data Index: 487626 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4710. Min Range: -5.4710
Max Act: 5.0023. Min Act: -0.1700
Data Index: 4507937 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4710. Min Range: -5.4710
Max Act: 5.0335. Min Act: -0.1700
Data Index: 1870415 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4710. Min Range: -5.4710
Max Act: 5.0335. Min Act: -0.1700
Data Index: 8420640 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4710. Min Range: -5.4710
Max Act: 5.0335. Min Act: -0.1700
Data Index: 4613228 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4710. Min Range: -5.4710
Max Act: 5.0335. Min Act: -0.1700
Data Index: 482510 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4710. Min Range: -5.4710
Max Act: 5.0023. Min Act: -0.1700
Data Index: 7963443 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4710. Min Range: -5.4710
Max Act: 5.0023. Min Act: -0.1700
Data Index: 2878147 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4710. Min Range: -5.4710
Max Act: 5.0023. Min Act: -0.1700
Data Index: 3473738 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4710. Min Range: -5.4710
Max Act: 5.0023. Min Act: -0.1700
Data Index: 3131799 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4710. Min Range: -5.4710
Max Act: 5.0023. Min Act: -0.1700
Data Index: 3755013 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4710. Min Range: -5.4710
Max Act: 5.0023. Min Act: -0.1700
Data Index: 3839605 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4710. Min Range: -5.4710
Max Act: 4.9710. Min Act: -0.1700
Data Index: 212446 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #19