Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1273 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1299. Min Range: -9.1299
Max Act: 9.1299. Min Act: -0.1700
Data Index: 7737070 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1299. Min Range: -9.1299
Max Act: 8.8799. Min Act: -0.1700
Data Index: 8238282 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1299. Min Range: -9.1299
Max Act: 8.7549. Min Act: -0.1700
Data Index: 907705 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1299. Min Range: -9.1299
Max Act: 8.7549. Min Act: -0.1700
Data Index: 3982185 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1299. Min Range: -9.1299
Max Act: 8.7549. Min Act: -0.1700
Data Index: 8377597 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1299. Min Range: -9.1299
Max Act: 8.7549. Min Act: -0.1700
Data Index: 185910 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1299. Min Range: -9.1299
Max Act: 8.6924. Min Act: -0.1700
Data Index: 1181477 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1299. Min Range: -9.1299
Max Act: 8.6924. Min Act: -0.1700
Data Index: 1684880 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1299. Min Range: -9.1299
Max Act: 8.6299. Min Act: -0.1700
Data Index: 21339 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1299. Min Range: -9.1299
Max Act: 8.5674. Min Act: -0.1700
Data Index: 7967044 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1299. Min Range: -9.1299
Max Act: 8.5674. Min Act: -0.1700
Data Index: 5316144 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1299. Min Range: -9.1299
Max Act: 8.5674. Min Act: -0.1700
Data Index: 5193182 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1299. Min Range: -9.1299
Max Act: 8.5674. Min Act: -0.1700
Data Index: 6244391 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1299. Min Range: -9.1299
Max Act: 8.5674. Min Act: -0.1700
Data Index: 5428745 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1299. Min Range: -9.1299
Max Act: 8.5674. Min Act: -0.1700
Data Index: 7616447 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1299. Min Range: -9.1299
Max Act: 8.6299. Min Act: -0.1700
Data Index: 8271142 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1299. Min Range: -9.1299
Max Act: 8.5674. Min Act: -0.1700
Data Index: 6643660 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1299. Min Range: -9.1299
Max Act: 8.5674. Min Act: -0.1700
Data Index: 2340836 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1299. Min Range: -9.1299
Max Act: 8.5674. Min Act: -0.1700
Data Index: 6270359 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1299. Min Range: -9.1299
Max Act: 8.5049. Min Act: -0.1700
Data Index: 4613477 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #19