Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5656 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8878. Min Range: -6.8878
Max Act: 6.8878. Min Act: -0.1700
Data Index: 8733785 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8878. Min Range: -6.8878
Max Act: 6.7941. Min Act: -0.1700
Data Index: 2214208 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8878. Min Range: -6.8878
Max Act: 6.7316. Min Act: -0.1700
Data Index: 2158149 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8878. Min Range: -6.8878
Max Act: 6.7316. Min Act: -0.1700
Data Index: 1460776 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8878. Min Range: -6.8878
Max Act: 6.7003. Min Act: -0.1700
Data Index: 2143839 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8878. Min Range: -6.8878
Max Act: 6.6691. Min Act: -0.1700
Data Index: 4272591 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8878. Min Range: -6.8878
Max Act: 6.6691. Min Act: -0.1700
Data Index: 6147762 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8878. Min Range: -6.8878
Max Act: 6.5441. Min Act: -0.1700
Data Index: 5384454 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8878. Min Range: -6.8878
Max Act: 6.5128. Min Act: -0.1700
Data Index: 6725177 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8878. Min Range: -6.8878
Max Act: 6.5128. Min Act: -0.1700
Data Index: 6607420 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8878. Min Range: -6.8878
Max Act: 6.5441. Min Act: -0.1700
Data Index: 8590959 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8878. Min Range: -6.8878
Max Act: 6.5128. Min Act: -0.1700
Data Index: 4608857 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8878. Min Range: -6.8878
Max Act: 6.4816. Min Act: -0.1700
Data Index: 5015569 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8878. Min Range: -6.8878
Max Act: 6.4503. Min Act: -0.1700
Data Index: 7446935 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8878. Min Range: -6.8878
Max Act: 6.4503. Min Act: -0.1700
Data Index: 6309523 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8878. Min Range: -6.8878
Max Act: 6.4503. Min Act: -0.1700
Data Index: 37535 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8878. Min Range: -6.8878
Max Act: 6.4191. Min Act: -0.1700
Data Index: 8624741 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8878. Min Range: -6.8878
Max Act: 6.3878. Min Act: -0.1700
Data Index: 3594490 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8878. Min Range: -6.8878
Max Act: 6.3878. Min Act: -0.1700
Data Index: 7979721 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8878. Min Range: -6.8878
Max Act: 6.3566. Min Act: -0.1700
Data Index: 4500597 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #19