Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3972 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2014. Min Range: -5.2014
Max Act: 5.2014. Min Act: -0.1700
Data Index: 2910243 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2014. Min Range: -5.2014
Max Act: 4.9514. Min Act: -0.1700
Data Index: 5557444 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2014. Min Range: -5.2014
Max Act: 4.9514. Min Act: -0.1700
Data Index: 113420 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2014. Min Range: -5.2014
Max Act: 4.8889. Min Act: -0.1700
Data Index: 2725480 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2014. Min Range: -5.2014
Max Act: 4.8264. Min Act: -0.1700
Data Index: 725571 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2014. Min Range: -5.2014
Max Act: 4.7951. Min Act: -0.1700
Data Index: 4259343 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2014. Min Range: -5.2014
Max Act: 4.8576. Min Act: -0.1700
Data Index: 4259340 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2014. Min Range: -5.2014
Max Act: 4.8576. Min Act: -0.1700
Data Index: 570065 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2014. Min Range: -5.2014
Max Act: 4.7951. Min Act: -0.1700
Data Index: 7805972 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2014. Min Range: -5.2014
Max Act: 4.7639. Min Act: -0.1700
Data Index: 4145978 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2014. Min Range: -5.2014
Max Act: 4.7639. Min Act: -0.1700
Data Index: 593557 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2014. Min Range: -5.2014
Max Act: 4.7639. Min Act: -0.1700
Data Index: 3713582 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2014. Min Range: -5.2014
Max Act: 4.7326. Min Act: -0.1700
Data Index: 7805968 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2014. Min Range: -5.2014
Max Act: 4.7326. Min Act: -0.1700
Data Index: 7805974 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2014. Min Range: -5.2014
Max Act: 4.7326. Min Act: -0.1700
Data Index: 7805946 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2014. Min Range: -5.2014
Max Act: 4.7639. Min Act: -0.1700
Data Index: 8168244 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2014. Min Range: -5.2014
Max Act: 4.7326. Min Act: -0.1700
Data Index: 7805976 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2014. Min Range: -5.2014
Max Act: 4.7326. Min Act: -0.1700
Data Index: 7805947 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2014. Min Range: -5.2014
Max Act: 4.7014. Min Act: -0.1700
Data Index: 7068398 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2014. Min Range: -5.2014
Max Act: 4.6701. Min Act: -0.1700
Data Index: 4500885 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #19