Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4431 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0746. Min Range: -4.0746
Max Act: 4.0746. Min Act: -0.1700
Data Index: 8113489 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0746. Min Range: -4.0746
Max Act: 4.0433. Min Act: -0.1700
Data Index: 4300027 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0746. Min Range: -4.0746
Max Act: 4.0120. Min Act: -0.1700
Data Index: 6300038 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0746. Min Range: -4.0746
Max Act: 3.9183. Min Act: -0.1700
Data Index: 6246056 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0746. Min Range: -4.0746
Max Act: 3.9495. Min Act: -0.1700
Data Index: 4036977 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0746. Min Range: -4.0746
Max Act: 3.9183. Min Act: -0.1700
Data Index: 5286425 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0746. Min Range: -4.0746
Max Act: 3.9495. Min Act: -0.1700
Data Index: 7011022 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0746. Min Range: -4.0746
Max Act: 3.8870. Min Act: -0.1700
Data Index: 8624984 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0746. Min Range: -4.0746
Max Act: 3.9183. Min Act: -0.1700
Data Index: 3141161 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0746. Min Range: -4.0746
Max Act: 3.8870. Min Act: -0.1700
Data Index: 4858382 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0746. Min Range: -4.0746
Max Act: 3.8870. Min Act: -0.1700
Data Index: 8052520 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0746. Min Range: -4.0746
Max Act: 3.8557. Min Act: -0.1700
Data Index: 5475737 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0746. Min Range: -4.0746
Max Act: 3.8557. Min Act: -0.1700
Data Index: 7111579 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0746. Min Range: -4.0746
Max Act: 3.8557. Min Act: -0.1700
Data Index: 1565900 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0746. Min Range: -4.0746
Max Act: 3.8557. Min Act: -0.1700
Data Index: 724213 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0746. Min Range: -4.0746
Max Act: 3.8245. Min Act: -0.1700
Data Index: 3031913 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0746. Min Range: -4.0746
Max Act: 3.8245. Min Act: -0.1700
Data Index: 5970308 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0746. Min Range: -4.0746
Max Act: 3.8245. Min Act: -0.1700
Data Index: 641743 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0746. Min Range: -4.0746
Max Act: 3.8245. Min Act: -0.1700
Data Index: 7931493 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0746. Min Range: -4.0746
Max Act: 3.8245. Min Act: -0.1700
Data Index: 6770774 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19