Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6178 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6972. Min Range: -7.6972
Max Act: 7.6972. Min Act: -0.1700
Data Index: 8339720 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6972. Min Range: -7.6972
Max Act: 7.4472. Min Act: -0.1700
Data Index: 1024841 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6972. Min Range: -7.6972
Max Act: 7.3847. Min Act: -0.1700
Data Index: 722317 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6972. Min Range: -7.6972
Max Act: 7.3222. Min Act: -0.1700
Data Index: 3553696 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6972. Min Range: -7.6972
Max Act: 7.2909. Min Act: -0.1700
Data Index: 2148753 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6972. Min Range: -7.6972
Max Act: 7.2597. Min Act: -0.1700
Data Index: 4268969 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6972. Min Range: -7.6972
Max Act: 7.2597. Min Act: -0.1700
Data Index: 5274849 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6972. Min Range: -7.6972
Max Act: 7.2284. Min Act: -0.1700
Data Index: 7789326 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6972. Min Range: -7.6972
Max Act: 7.2284. Min Act: -0.1700
Data Index: 5766625 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6972. Min Range: -7.6972
Max Act: 7.2284. Min Act: -0.1700
Data Index: 3772498 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6972. Min Range: -7.6972
Max Act: 7.1972. Min Act: -0.1700
Data Index: 8718787 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6972. Min Range: -7.6972
Max Act: 7.1659. Min Act: -0.1700
Data Index: 5724342 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6972. Min Range: -7.6972
Max Act: 7.1659. Min Act: -0.1700
Data Index: 4558860 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6972. Min Range: -7.6972
Max Act: 7.1034. Min Act: -0.1700
Data Index: 6000370 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6972. Min Range: -7.6972
Max Act: 7.1034. Min Act: -0.1700
Data Index: 6115357 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6972. Min Range: -7.6972
Max Act: 7.0722. Min Act: -0.1700
Data Index: 939834 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6972. Min Range: -7.6972
Max Act: 7.0722. Min Act: -0.1700
Data Index: 7027900 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6972. Min Range: -7.6972
Max Act: 7.0722. Min Act: -0.1700
Data Index: 470611 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6972. Min Range: -7.6972
Max Act: 7.0097. Min Act: -0.1700
Data Index: 5067300 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6972. Min Range: -7.6972
Max Act: 7.0409. Min Act: -0.1700
Data Index: 5075271 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #19