Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3674 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2308. Min Range: -8.2308
Max Act: 8.2308. Min Act: -0.1700
Data Index: 8650974 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2308. Min Range: -8.2308
Max Act: 7.6996. Min Act: -0.1700
Data Index: 7927602 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2308. Min Range: -8.2308
Max Act: 7.3246. Min Act: -0.1700
Data Index: 5665103 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2308. Min Range: -8.2308
Max Act: 7.1996. Min Act: -0.1700
Data Index: 2422066 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2308. Min Range: -8.2308
Max Act: 7.1371. Min Act: -0.1700
Data Index: 656012 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2308. Min Range: -8.2308
Max Act: 7.1683. Min Act: -0.1700
Data Index: 1081863 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2308. Min Range: -8.2308
Max Act: 7.1683. Min Act: -0.1700
Data Index: 2588839 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2308. Min Range: -8.2308
Max Act: 7.1058. Min Act: -0.1700
Data Index: 167943 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2308. Min Range: -8.2308
Max Act: 7.0746. Min Act: -0.1700
Data Index: 3328515 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2308. Min Range: -8.2308
Max Act: 7.0746. Min Act: -0.1700
Data Index: 7010816 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2308. Min Range: -8.2308
Max Act: 7.0433. Min Act: -0.1700
Data Index: 996094 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2308. Min Range: -8.2308
Max Act: 7.0121. Min Act: -0.1700
Data Index: 3798586 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2308. Min Range: -8.2308
Max Act: 7.0121. Min Act: -0.1700
Data Index: 7725858 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2308. Min Range: -8.2308
Max Act: 7.0121. Min Act: -0.1700
Data Index: 7927603 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2308. Min Range: -8.2308
Max Act: 6.9808. Min Act: -0.1700
Data Index: 1831335 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2308. Min Range: -8.2308
Max Act: 7.0121. Min Act: -0.1700
Data Index: 7078964 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2308. Min Range: -8.2308
Max Act: 7.0121. Min Act: -0.1700
Data Index: 7008836 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2308. Min Range: -8.2308
Max Act: 6.9496. Min Act: -0.1700
Data Index: 7891245 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2308. Min Range: -8.2308
Max Act: 6.9496. Min Act: -0.1700
Data Index: 8349615 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2308. Min Range: -8.2308
Max Act: 6.9496. Min Act: -0.1700
Data Index: 1700338 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #19