Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6338 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8557. Min Range: -6.8557
Max Act: 6.8557. Min Act: -0.1700
Data Index: 4767412 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8557. Min Range: -6.8557
Max Act: 6.6995. Min Act: -0.1700
Data Index: 1698256 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8557. Min Range: -6.8557
Max Act: 6.6682. Min Act: -0.1700
Data Index: 4944198 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8557. Min Range: -6.8557
Max Act: 6.6682. Min Act: -0.1700
Data Index: 5569937 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8557. Min Range: -6.8557
Max Act: 6.5745. Min Act: -0.1700
Data Index: 6161904 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8557. Min Range: -6.8557
Max Act: 6.6057. Min Act: -0.1700
Data Index: 7776 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8557. Min Range: -6.8557
Max Act: 6.5745. Min Act: -0.1700
Data Index: 5668625 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8557. Min Range: -6.8557
Max Act: 6.5432. Min Act: -0.1700
Data Index: 8431709 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8557. Min Range: -6.8557
Max Act: 6.5432. Min Act: -0.1700
Data Index: 817819 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8557. Min Range: -6.8557
Max Act: 6.5120. Min Act: -0.1700
Data Index: 6195572 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8557. Min Range: -6.8557
Max Act: 6.5120. Min Act: -0.1700
Data Index: 8452787 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8557. Min Range: -6.8557
Max Act: 6.5120. Min Act: -0.1700
Data Index: 5211236 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8557. Min Range: -6.8557
Max Act: 6.4807. Min Act: -0.1700
Data Index: 6553175 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8557. Min Range: -6.8557
Max Act: 6.4807. Min Act: -0.1700
Data Index: 1136902 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8557. Min Range: -6.8557
Max Act: 6.4495. Min Act: -0.1700
Data Index: 1027455 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8557. Min Range: -6.8557
Max Act: 6.4495. Min Act: -0.1700
Data Index: 3305642 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8557. Min Range: -6.8557
Max Act: 6.4182. Min Act: -0.1700
Data Index: 4224456 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8557. Min Range: -6.8557
Max Act: 6.3557. Min Act: -0.1700
Data Index: 6445515 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8557. Min Range: -6.8557
Max Act: 6.3870. Min Act: -0.1700
Data Index: 6982222 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8557. Min Range: -6.8557
Max Act: 6.3870. Min Act: -0.1700
Data Index: 8124373 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #19