Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1301 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7057. Min Range: -7.7057
Max Act: 7.7057. Min Act: -0.1700
Data Index: 1988333 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7057. Min Range: -7.7057
Max Act: 7.2995. Min Act: -0.1700
Data Index: 4166855 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7057. Min Range: -7.7057
Max Act: 7.2682. Min Act: -0.1700
Data Index: 1603637 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7057. Min Range: -7.7057
Max Act: 7.2370. Min Act: -0.1700
Data Index: 6523115 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7057. Min Range: -7.7057
Max Act: 7.1432. Min Act: -0.1700
Data Index: 508277 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7057. Min Range: -7.7057
Max Act: 7.0495. Min Act: -0.1700
Data Index: 4601254 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7057. Min Range: -7.7057
Max Act: 7.0495. Min Act: -0.1700
Data Index: 5880854 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7057. Min Range: -7.7057
Max Act: 7.0495. Min Act: -0.1700
Data Index: 7219427 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7057. Min Range: -7.7057
Max Act: 7.0495. Min Act: -0.1700
Data Index: 913109 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7057. Min Range: -7.7057
Max Act: 6.9870. Min Act: -0.1700
Data Index: 6388327 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7057. Min Range: -7.7057
Max Act: 6.9557. Min Act: -0.1700
Data Index: 6902303 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7057. Min Range: -7.7057
Max Act: 6.9557. Min Act: -0.1700
Data Index: 1558939 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7057. Min Range: -7.7057
Max Act: 6.9245. Min Act: -0.1700
Data Index: 8181614 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7057. Min Range: -7.7057
Max Act: 6.8932. Min Act: -0.1700
Data Index: 3272401 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7057. Min Range: -7.7057
Max Act: 6.8620. Min Act: -0.1700
Data Index: 274675 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7057. Min Range: -7.7057
Max Act: 6.7995. Min Act: -0.1700
Data Index: 5029178 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7057. Min Range: -7.7057
Max Act: 6.8307. Min Act: -0.1700
Data Index: 3524037 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7057. Min Range: -7.7057
Max Act: 6.7995. Min Act: -0.1700
Data Index: 7292980 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7057. Min Range: -7.7057
Max Act: 6.7682. Min Act: -0.1700
Data Index: 6000365 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7057. Min Range: -7.7057
Max Act: 6.7682. Min Act: -0.1700
Data Index: 2007860 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #19