Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3566 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.0481. Min Range: -2.0481
Max Act: 2.0481. Min Act: -0.1700
Data Index: 1921247 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0481. Min Range: -2.0481
Max Act: 1.9636. Min Act: -0.1696
Data Index: 7355763 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0481. Min Range: -2.0481
Max Act: 1.9467. Min Act: -0.1700
Data Index: 2460313 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0481. Min Range: -2.0481
Max Act: 1.9127. Min Act: -0.1698
Data Index: 7355764 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0481. Min Range: -2.0481
Max Act: 1.8614. Min Act: -0.1700
Data Index: 6997370 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0481. Min Range: -2.0481
Max Act: 1.8272. Min Act: -0.1700
Data Index: 5399874 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0481. Min Range: -2.0481
Max Act: 1.7928. Min Act: -0.1700
Data Index: 2142336 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0481. Min Range: -2.0481
Max Act: 1.7583. Min Act: -0.1700
Data Index: 619817 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0481. Min Range: -2.0481
Max Act: 1.7583. Min Act: -0.1700
Data Index: 3393199 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0481. Min Range: -2.0481
Max Act: 1.7410. Min Act: -0.1700
Data Index: 5647477 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0481. Min Range: -2.0481
Max Act: 1.7237. Min Act: -0.1669
Data Index: 7783637 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0481. Min Range: -2.0481
Max Act: 1.6891. Min Act: -0.1700
Data Index: 5218293 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0481. Min Range: -2.0481
Max Act: 1.7064. Min Act: -0.1700
Data Index: 1862069 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0481. Min Range: -2.0481
Max Act: 1.6717. Min Act: -0.1688
Data Index: 960695 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0481. Min Range: -2.0481
Max Act: 1.6717. Min Act: -0.1700
Data Index: 7355762 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0481. Min Range: -2.0481
Max Act: 1.6717. Min Act: -0.1676
Data Index: 5250338 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0481. Min Range: -2.0481
Max Act: 1.6369. Min Act: -0.1598
Data Index: 2657193 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0481. Min Range: -2.0481
Max Act: 1.6543. Min Act: -0.1691
Data Index: 1775156 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0481. Min Range: -2.0481
Max Act: 1.6369. Min Act: -0.1700
Data Index: 3455426 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0481. Min Range: -2.0481
Max Act: 1.6369. Min Act: -0.1700
Data Index: 5753144 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #19