Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 341 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1662. Min Range: -7.1662
Max Act: 7.1662. Min Act: -0.1700
Data Index: 1235819 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1662. Min Range: -7.1662
Max Act: 7.0100. Min Act: -0.1700
Data Index: 1361407 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1662. Min Range: -7.1662
Max Act: 6.9162. Min Act: -0.1700
Data Index: 8781209 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1662. Min Range: -7.1662
Max Act: 6.6975. Min Act: -0.1700
Data Index: 2769704 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1662. Min Range: -7.1662
Max Act: 6.6037. Min Act: -0.1700
Data Index: 6228881 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1662. Min Range: -7.1662
Max Act: 6.5725. Min Act: -0.1700
Data Index: 984069 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1662. Min Range: -7.1662
Max Act: 6.5100. Min Act: -0.1700
Data Index: 4861589 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1662. Min Range: -7.1662
Max Act: 6.5412. Min Act: -0.1700
Data Index: 5846186 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1662. Min Range: -7.1662
Max Act: 6.4787. Min Act: -0.1700
Data Index: 8714444 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1662. Min Range: -7.1662
Max Act: 6.4162. Min Act: -0.1700
Data Index: 6092124 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1662. Min Range: -7.1662
Max Act: 6.4162. Min Act: -0.1700
Data Index: 3675077 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1662. Min Range: -7.1662
Max Act: 6.3850. Min Act: -0.1700
Data Index: 7095988 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1662. Min Range: -7.1662
Max Act: 6.3537. Min Act: -0.1700
Data Index: 7191801 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1662. Min Range: -7.1662
Max Act: 6.3537. Min Act: -0.1700
Data Index: 1951304 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1662. Min Range: -7.1662
Max Act: 6.2912. Min Act: -0.1700
Data Index: 5148095 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1662. Min Range: -7.1662
Max Act: 6.3225. Min Act: -0.1700
Data Index: 1156649 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1662. Min Range: -7.1662
Max Act: 6.2912. Min Act: -0.1700
Data Index: 2642942 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1662. Min Range: -7.1662
Max Act: 6.2912. Min Act: -0.1700
Data Index: 4544583 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1662. Min Range: -7.1662
Max Act: 6.2912. Min Act: -0.1700
Data Index: 6433920 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1662. Min Range: -7.1662
Max Act: 6.2912. Min Act: -0.1700
Data Index: 5065607 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #19