Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2060 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.1562. Min Act: -0.1700
Data Index: 5644116 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.1562. Min Act: -0.1700
Data Index: 8148619 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.1562. Min Act: -0.1700
Data Index: 6674650 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.1562. Min Act: -0.1700
Data Index: 3216960 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.1405. Min Act: -0.1700
Data Index: 4388013 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.1090. Min Act: -0.1700
Data Index: 2373258 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.1248. Min Act: -0.1700
Data Index: 3139425 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.1248. Min Act: -0.1700
Data Index: 6948556 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.1248. Min Act: -0.1700
Data Index: 5137971 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.1248. Min Act: -0.1700
Data Index: 6090731 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.1090. Min Act: -0.1700
Data Index: 2082847 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.1090. Min Act: -0.1700
Data Index: 7649850 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.1090. Min Act: -0.1700
Data Index: 8504894 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.0932. Min Act: -0.1700
Data Index: 2609612 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.0617. Min Act: -0.1700
Data Index: 7694096 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.0775. Min Act: -0.1700
Data Index: 3045546 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.0775. Min Act: -0.1700
Data Index: 4771541 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.0775. Min Act: -0.1700
Data Index: 2346144 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.0617. Min Act: -0.1700
Data Index: 308284 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1562. Min Range: -3.1562
Max Act: 3.0932. Min Act: -0.1700
Data Index: 6565221 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #19