Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4677 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1432. Min Range: -5.1432
Max Act: 5.1432. Min Act: -0.1700
Data Index: 3071371 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1432. Min Range: -5.1432
Max Act: 5.0807. Min Act: -0.1700
Data Index: 1024940 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1432. Min Range: -5.1432
Max Act: 4.9557. Min Act: -0.1700
Data Index: 8606545 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1432. Min Range: -5.1432
Max Act: 4.9557. Min Act: -0.1700
Data Index: 7463291 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1432. Min Range: -5.1432
Max Act: 4.9244. Min Act: -0.1700
Data Index: 1596343 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1432. Min Range: -5.1432
Max Act: 4.9244. Min Act: -0.1700
Data Index: 6075796 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1432. Min Range: -5.1432
Max Act: 4.8932. Min Act: -0.1700
Data Index: 407730 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1432. Min Range: -5.1432
Max Act: 4.8932. Min Act: -0.1700
Data Index: 6654272 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1432. Min Range: -5.1432
Max Act: 4.8932. Min Act: -0.1700
Data Index: 228879 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1432. Min Range: -5.1432
Max Act: 4.8619. Min Act: -0.1700
Data Index: 1290491 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1432. Min Range: -5.1432
Max Act: 4.8619. Min Act: -0.1700
Data Index: 5766207 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1432. Min Range: -5.1432
Max Act: 4.8307. Min Act: -0.1700
Data Index: 192587 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1432. Min Range: -5.1432
Max Act: 4.8307. Min Act: -0.1700
Data Index: 1986503 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1432. Min Range: -5.1432
Max Act: 4.7994. Min Act: -0.1700
Data Index: 2951035 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1432. Min Range: -5.1432
Max Act: 4.7682. Min Act: -0.1700
Data Index: 6323117 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1432. Min Range: -5.1432
Max Act: 4.7994. Min Act: -0.1700
Data Index: 1380508 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1432. Min Range: -5.1432
Max Act: 4.8307. Min Act: -0.1700
Data Index: 6573651 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1432. Min Range: -5.1432
Max Act: 4.7682. Min Act: -0.1700
Data Index: 4785700 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1432. Min Range: -5.1432
Max Act: 4.7994. Min Act: -0.1700
Data Index: 2423408 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1432. Min Range: -5.1432
Max Act: 4.7682. Min Act: -0.1700
Data Index: 5580902 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #19