Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4600 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.8240. Min Act: -0.1700
Data Index: 8793156 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.6678. Min Act: -0.1700
Data Index: 3726070 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.2928. Min Act: -0.1700
Data Index: 4190358 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.2615. Min Act: -0.1700
Data Index: 2810973 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.2615. Min Act: -0.1700
Data Index: 1259250 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.1990. Min Act: -0.1700
Data Index: 8756221 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.1990. Min Act: -0.1700
Data Index: 669012 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.1678. Min Act: -0.1700
Data Index: 793686 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.1053. Min Act: -0.1700
Data Index: 128870 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.1365. Min Act: -0.1700
Data Index: 370930 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.1365. Min Act: -0.1700
Data Index: 2894906 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.1365. Min Act: -0.1700
Data Index: 793685 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.1365. Min Act: -0.1700
Data Index: 8188315 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.1678. Min Act: -0.1700
Data Index: 7488520 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.1365. Min Act: -0.1700
Data Index: 8311629 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.1365. Min Act: -0.1700
Data Index: 2686155 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.0740. Min Act: -0.1700
Data Index: 1803758 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.1053. Min Act: -0.1700
Data Index: 5470825 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.0740. Min Act: -0.1700
Data Index: 1251469 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.1053. Min Act: -0.1700
Data Index: 4509079 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #19