Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 957 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2700. Min Range: -5.2700
Max Act: 5.2700. Min Act: -0.1700
Data Index: 8696246 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2700. Min Range: -5.2700
Max Act: 5.2700. Min Act: -0.1700
Data Index: 189853 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2700. Min Range: -5.2700
Max Act: 5.2387. Min Act: -0.1700
Data Index: 5854803 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2700. Min Range: -5.2700
Max Act: 5.2075. Min Act: -0.1700
Data Index: 2159338 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2700. Min Range: -5.2700
Max Act: 5.1762. Min Act: -0.1700
Data Index: 7871422 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2700. Min Range: -5.2700
Max Act: 5.2075. Min Act: -0.1700
Data Index: 2783494 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2700. Min Range: -5.2700
Max Act: 5.1762. Min Act: -0.1700
Data Index: 6989976 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2700. Min Range: -5.2700
Max Act: 5.1450. Min Act: -0.1700
Data Index: 1313093 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2700. Min Range: -5.2700
Max Act: 5.1762. Min Act: -0.1700
Data Index: 4902461 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2700. Min Range: -5.2700
Max Act: 5.1450. Min Act: -0.1700
Data Index: 2928130 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2700. Min Range: -5.2700
Max Act: 5.1450. Min Act: -0.1700
Data Index: 4701973 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2700. Min Range: -5.2700
Max Act: 5.1450. Min Act: -0.1700
Data Index: 2594273 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2700. Min Range: -5.2700
Max Act: 5.1450. Min Act: -0.1700
Data Index: 4228966 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2700. Min Range: -5.2700
Max Act: 5.1450. Min Act: -0.1700
Data Index: 7978097 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2700. Min Range: -5.2700
Max Act: 5.1137. Min Act: -0.1700
Data Index: 4728266 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2700. Min Range: -5.2700
Max Act: 5.0825. Min Act: -0.1700
Data Index: 251743 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2700. Min Range: -5.2700
Max Act: 5.1137. Min Act: -0.1700
Data Index: 622687 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2700. Min Range: -5.2700
Max Act: 5.0825. Min Act: -0.1700
Data Index: 3455580 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2700. Min Range: -5.2700
Max Act: 5.0825. Min Act: -0.1700
Data Index: 1009378 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2700. Min Range: -5.2700
Max Act: 5.0825. Min Act: -0.1700
Data Index: 5427685 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #19