Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5803 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4971. Min Range: -6.4971
Max Act: 6.4971. Min Act: -0.1700
Data Index: 7852572 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4971. Min Range: -6.4971
Max Act: 6.4658. Min Act: -0.1700
Data Index: 7852598 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4971. Min Range: -6.4971
Max Act: 6.1846. Min Act: -0.1700
Data Index: 2127367 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4971. Min Range: -6.4971
Max Act: 6.1846. Min Act: -0.1700
Data Index: 5816446 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4971. Min Range: -6.4971
Max Act: 6.1846. Min Act: -0.1700
Data Index: 4555446 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4971. Min Range: -6.4971
Max Act: 6.0908. Min Act: -0.1700
Data Index: 3596955 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4971. Min Range: -6.4971
Max Act: 6.0283. Min Act: -0.1700
Data Index: 8090947 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4971. Min Range: -6.4971
Max Act: 5.9971. Min Act: -0.1700
Data Index: 90376 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4971. Min Range: -6.4971
Max Act: 5.9033. Min Act: -0.1700
Data Index: 5147192 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4971. Min Range: -6.4971
Max Act: 5.8721. Min Act: -0.1700
Data Index: 7459164 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4971. Min Range: -6.4971
Max Act: 5.8721. Min Act: -0.1700
Data Index: 7372709 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4971. Min Range: -6.4971
Max Act: 5.8408. Min Act: -0.1700
Data Index: 2925962 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4971. Min Range: -6.4971
Max Act: 5.8408. Min Act: -0.1700
Data Index: 3291757 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4971. Min Range: -6.4971
Max Act: 5.7783. Min Act: -0.1700
Data Index: 1125012 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4971. Min Range: -6.4971
Max Act: 5.7783. Min Act: -0.1700
Data Index: 7294507 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4971. Min Range: -6.4971
Max Act: 5.7471. Min Act: -0.1700
Data Index: 6175940 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4971. Min Range: -6.4971
Max Act: 5.7783. Min Act: -0.1700
Data Index: 2993482 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4971. Min Range: -6.4971
Max Act: 5.7471. Min Act: -0.1700
Data Index: 3966235 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4971. Min Range: -6.4971
Max Act: 5.7471. Min Act: -0.1700
Data Index: 6753444 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4971. Min Range: -6.4971
Max Act: 5.7471. Min Act: -0.1700
Data Index: 4912107 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #19