Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 783 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4877. Min Range: -5.4877
Max Act: 5.4877. Min Act: -0.1700
Data Index: 1341057 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4877. Min Range: -5.4877
Max Act: 5.4877. Min Act: -0.1700
Data Index: 8098737 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4877. Min Range: -5.4877
Max Act: 5.4877. Min Act: -0.1700
Data Index: 5689117 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4877. Min Range: -5.4877
Max Act: 5.4564. Min Act: -0.1700
Data Index: 7364103 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4877. Min Range: -5.4877
Max Act: 5.4252. Min Act: -0.1700
Data Index: 1324858 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4877. Min Range: -5.4877
Max Act: 5.4252. Min Act: -0.1700
Data Index: 1508011 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4877. Min Range: -5.4877
Max Act: 5.3939. Min Act: -0.1700
Data Index: 3478019 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4877. Min Range: -5.4877
Max Act: 5.3939. Min Act: -0.1700
Data Index: 2617146 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4877. Min Range: -5.4877
Max Act: 5.3939. Min Act: -0.1700
Data Index: 1749307 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4877. Min Range: -5.4877
Max Act: 5.3939. Min Act: -0.1700
Data Index: 1507989 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4877. Min Range: -5.4877
Max Act: 5.3627. Min Act: -0.1700
Data Index: 7088836 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4877. Min Range: -5.4877
Max Act: 5.2689. Min Act: -0.1700
Data Index: 6050271 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4877. Min Range: -5.4877
Max Act: 5.2689. Min Act: -0.1700
Data Index: 4940353 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4877. Min Range: -5.4877
Max Act: 5.2689. Min Act: -0.1700
Data Index: 1749302 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4877. Min Range: -5.4877
Max Act: 5.2064. Min Act: -0.1700
Data Index: 5942149 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4877. Min Range: -5.4877
Max Act: 5.1752. Min Act: -0.1700
Data Index: 6425963 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4877. Min Range: -5.4877
Max Act: 5.1439. Min Act: -0.1700
Data Index: 773818 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4877. Min Range: -5.4877
Max Act: 5.1127. Min Act: -0.1700
Data Index: 1956347 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4877. Min Range: -5.4877
Max Act: 5.1127. Min Act: -0.1700
Data Index: 34426 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4877. Min Range: -5.4877
Max Act: 5.0814. Min Act: -0.1700
Data Index: 5921877 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #19