Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2456 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7160. Min Range: -2.7160
Max Act: 2.7000. Min Act: -0.1700
Data Index: 4104840 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7160. Min Range: -2.7160
Max Act: 2.7160. Min Act: -0.1700
Data Index: 7903432 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7160. Min Range: -2.7160
Max Act: 2.6519. Min Act: -0.1700
Data Index: 754671 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7160. Min Range: -2.7160
Max Act: 2.6359. Min Act: -0.1700
Data Index: 1073423 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7160. Min Range: -2.7160
Max Act: 2.6037. Min Act: -0.1700
Data Index: 2706158 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7160. Min Range: -2.7160
Max Act: 2.6037. Min Act: -0.1700
Data Index: 568627 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7160. Min Range: -2.7160
Max Act: 2.6037. Min Act: -0.1700
Data Index: 7886322 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7160. Min Range: -2.7160
Max Act: 2.5876. Min Act: -0.1700
Data Index: 5641732 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7160. Min Range: -2.7160
Max Act: 2.5554. Min Act: -0.1641
Data Index: 4477750 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7160. Min Range: -2.7160
Max Act: 2.5715. Min Act: -0.1700
Data Index: 7756307 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7160. Min Range: -2.7160
Max Act: 2.5715. Min Act: -0.1700
Data Index: 5676860 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7160. Min Range: -2.7160
Max Act: 2.5554. Min Act: -0.1700
Data Index: 652801 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7160. Min Range: -2.7160
Max Act: 2.5554. Min Act: -0.1700
Data Index: 6171917 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7160. Min Range: -2.7160
Max Act: 2.5554. Min Act: -0.1700
Data Index: 4754676 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7160. Min Range: -2.7160
Max Act: 2.5392. Min Act: -0.1700
Data Index: 5516877 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7160. Min Range: -2.7160
Max Act: 2.5231. Min Act: -0.1700
Data Index: 5984052 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7160. Min Range: -2.7160
Max Act: 2.5392. Min Act: -0.1700
Data Index: 8107366 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7160. Min Range: -2.7160
Max Act: 2.5392. Min Act: -0.1700
Data Index: 6290410 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7160. Min Range: -2.7160
Max Act: 2.5231. Min Act: -0.1700
Data Index: 1622753 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7160. Min Range: -2.7160
Max Act: 2.5231. Min Act: -0.1700
Data Index: 3593824 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #19