Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 456 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8284. Min Range: -5.8284
Max Act: 5.8284. Min Act: -0.1700
Data Index: 3234973 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8284. Min Range: -5.8284
Max Act: 5.7659. Min Act: -0.1700
Data Index: 7690146 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8284. Min Range: -5.8284
Max Act: 5.5472. Min Act: -0.1700
Data Index: 6443986 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8284. Min Range: -5.8284
Max Act: 5.5159. Min Act: -0.1700
Data Index: 1871109 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8284. Min Range: -5.8284
Max Act: 5.5159. Min Act: -0.1700
Data Index: 2848717 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8284. Min Range: -5.8284
Max Act: 5.4847. Min Act: -0.1700
Data Index: 1640608 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8284. Min Range: -5.8284
Max Act: 5.4534. Min Act: -0.1700
Data Index: 5063049 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8284. Min Range: -5.8284
Max Act: 5.4534. Min Act: -0.1700
Data Index: 1988713 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8284. Min Range: -5.8284
Max Act: 5.4222. Min Act: -0.1700
Data Index: 7075832 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8284. Min Range: -5.8284
Max Act: 5.3909. Min Act: -0.1700
Data Index: 4392950 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8284. Min Range: -5.8284
Max Act: 5.3909. Min Act: -0.1700
Data Index: 5616371 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8284. Min Range: -5.8284
Max Act: 5.3909. Min Act: -0.1700
Data Index: 1827832 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8284. Min Range: -5.8284
Max Act: 5.3909. Min Act: -0.1700
Data Index: 2583326 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8284. Min Range: -5.8284
Max Act: 5.3597. Min Act: -0.1700
Data Index: 1032172 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8284. Min Range: -5.8284
Max Act: 5.3909. Min Act: -0.1700
Data Index: 8050741 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8284. Min Range: -5.8284
Max Act: 5.3597. Min Act: -0.1700
Data Index: 3475633 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8284. Min Range: -5.8284
Max Act: 5.3597. Min Act: -0.1700
Data Index: 4695471 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8284. Min Range: -5.8284
Max Act: 5.3597. Min Act: -0.1700
Data Index: 7031909 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8284. Min Range: -5.8284
Max Act: 5.3284. Min Act: -0.1700
Data Index: 175175 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8284. Min Range: -5.8284
Max Act: 5.3597. Min Act: -0.1700
Data Index: 7624602 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #19