Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3889 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1318. Min Range: -6.1318
Max Act: 6.1318. Min Act: -0.1700
Data Index: 419936 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1318. Min Range: -6.1318
Max Act: 5.9755. Min Act: -0.1700
Data Index: 624916 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1318. Min Range: -6.1318
Max Act: 5.6318. Min Act: -0.1700
Data Index: 6600574 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1318. Min Range: -6.1318
Max Act: 5.5693. Min Act: -0.1700
Data Index: 3799788 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1318. Min Range: -6.1318
Max Act: 5.5380. Min Act: -0.1700
Data Index: 4941687 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1318. Min Range: -6.1318
Max Act: 5.5380. Min Act: -0.1700
Data Index: 1187625 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1318. Min Range: -6.1318
Max Act: 5.5380. Min Act: -0.1700
Data Index: 2130502 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1318. Min Range: -6.1318
Max Act: 5.4755. Min Act: -0.1700
Data Index: 8225042 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1318. Min Range: -6.1318
Max Act: 5.4755. Min Act: -0.1700
Data Index: 8792978 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1318. Min Range: -6.1318
Max Act: 5.4443. Min Act: -0.1700
Data Index: 383289 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1318. Min Range: -6.1318
Max Act: 5.4130. Min Act: -0.1700
Data Index: 2030501 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1318. Min Range: -6.1318
Max Act: 5.4130. Min Act: -0.1700
Data Index: 1444145 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1318. Min Range: -6.1318
Max Act: 5.3818. Min Act: -0.1700
Data Index: 2981622 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1318. Min Range: -6.1318
Max Act: 5.3505. Min Act: -0.1700
Data Index: 6785458 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1318. Min Range: -6.1318
Max Act: 5.3818. Min Act: -0.1700
Data Index: 5561017 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1318. Min Range: -6.1318
Max Act: 5.3818. Min Act: -0.1700
Data Index: 6680632 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1318. Min Range: -6.1318
Max Act: 5.3505. Min Act: -0.1700
Data Index: 5578105 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1318. Min Range: -6.1318
Max Act: 5.3505. Min Act: -0.1700
Data Index: 1420788 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1318. Min Range: -6.1318
Max Act: 5.3505. Min Act: -0.1700
Data Index: 3688774 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1318. Min Range: -6.1318
Max Act: 5.3505. Min Act: -0.1700
Data Index: 7880 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #19