Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2915 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8509. Min Range: -4.8509
Max Act: 4.8509. Min Act: -0.1700
Data Index: 2095594 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8509. Min Range: -4.8509
Max Act: 4.7884. Min Act: -0.1700
Data Index: 7756295 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8509. Min Range: -4.8509
Max Act: 4.6634. Min Act: -0.1700
Data Index: 8623948 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8509. Min Range: -4.8509
Max Act: 4.6322. Min Act: -0.1700
Data Index: 8783684 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8509. Min Range: -4.8509
Max Act: 4.6009. Min Act: -0.1700
Data Index: 4532849 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8509. Min Range: -4.8509
Max Act: 4.5697. Min Act: -0.1700
Data Index: 1680563 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8509. Min Range: -4.8509
Max Act: 4.6009. Min Act: -0.1700
Data Index: 3919917 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8509. Min Range: -4.8509
Max Act: 4.5384. Min Act: -0.1700
Data Index: 7761070 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8509. Min Range: -4.8509
Max Act: 4.5384. Min Act: -0.1700
Data Index: 403344 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8509. Min Range: -4.8509
Max Act: 4.5072. Min Act: -0.1700
Data Index: 469958 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8509. Min Range: -4.8509
Max Act: 4.5072. Min Act: -0.1700
Data Index: 7785757 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8509. Min Range: -4.8509
Max Act: 4.4447. Min Act: -0.1700
Data Index: 7182196 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8509. Min Range: -4.8509
Max Act: 4.5072. Min Act: -0.1700
Data Index: 3960533 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8509. Min Range: -4.8509
Max Act: 4.4447. Min Act: -0.1700
Data Index: 2494987 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8509. Min Range: -4.8509
Max Act: 4.4447. Min Act: -0.1700
Data Index: 5380201 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8509. Min Range: -4.8509
Max Act: 4.4447. Min Act: -0.1700
Data Index: 8588747 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8509. Min Range: -4.8509
Max Act: 4.4447. Min Act: -0.1700
Data Index: 6300278 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8509. Min Range: -4.8509
Max Act: 4.4447. Min Act: -0.1700
Data Index: 319811 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8509. Min Range: -4.8509
Max Act: 4.4447. Min Act: -0.1700
Data Index: 1246941 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8509. Min Range: -4.8509
Max Act: 4.4134. Min Act: -0.1700
Data Index: 2777755 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #19