Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2482 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1597. Min Range: -6.1597
Max Act: 6.1597. Min Act: -0.1700
Data Index: 7306387 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1597. Min Range: -6.1597
Max Act: 6.0972. Min Act: -0.1700
Data Index: 3493141 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1597. Min Range: -6.1597
Max Act: 6.0660. Min Act: -0.1700
Data Index: 4577600 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1597. Min Range: -6.1597
Max Act: 6.0347. Min Act: -0.1700
Data Index: 769628 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1597. Min Range: -6.1597
Max Act: 5.9410. Min Act: -0.1700
Data Index: 7407804 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1597. Min Range: -6.1597
Max Act: 5.9097. Min Act: -0.1700
Data Index: 30427 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1597. Min Range: -6.1597
Max Act: 5.9097. Min Act: -0.1700
Data Index: 1800214 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1597. Min Range: -6.1597
Max Act: 5.8785. Min Act: -0.1700
Data Index: 629508 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1597. Min Range: -6.1597
Max Act: 5.8785. Min Act: -0.1700
Data Index: 5766232 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1597. Min Range: -6.1597
Max Act: 5.8472. Min Act: -0.1700
Data Index: 1710685 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1597. Min Range: -6.1597
Max Act: 5.8472. Min Act: -0.1700
Data Index: 6424294 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1597. Min Range: -6.1597
Max Act: 5.7847. Min Act: -0.1700
Data Index: 2243419 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1597. Min Range: -6.1597
Max Act: 5.7847. Min Act: -0.1700
Data Index: 5996662 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1597. Min Range: -6.1597
Max Act: 5.7222. Min Act: -0.1700
Data Index: 4544283 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1597. Min Range: -6.1597
Max Act: 5.7535. Min Act: -0.1700
Data Index: 6650735 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1597. Min Range: -6.1597
Max Act: 5.6910. Min Act: -0.1700
Data Index: 16975 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1597. Min Range: -6.1597
Max Act: 5.6910. Min Act: -0.1700
Data Index: 7437985 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1597. Min Range: -6.1597
Max Act: 5.6910. Min Act: -0.1700
Data Index: 2301160 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1597. Min Range: -6.1597
Max Act: 5.6597. Min Act: -0.1700
Data Index: 2429539 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1597. Min Range: -6.1597
Max Act: 5.6285. Min Act: -0.1700
Data Index: 6426491 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #19