Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3135 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1005. Min Range: -6.1005
Max Act: 6.1005. Min Act: -0.1700
Data Index: 3352132 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1005. Min Range: -6.1005
Max Act: 6.0068. Min Act: -0.1700
Data Index: 68319 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1005. Min Range: -6.1005
Max Act: 5.9443. Min Act: -0.1700
Data Index: 1272967 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1005. Min Range: -6.1005
Max Act: 5.9443. Min Act: -0.1700
Data Index: 7486442 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1005. Min Range: -6.1005
Max Act: 5.9443. Min Act: -0.1700
Data Index: 658836 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1005. Min Range: -6.1005
Max Act: 5.9443. Min Act: -0.1700
Data Index: 4403238 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1005. Min Range: -6.1005
Max Act: 5.9130. Min Act: -0.1700
Data Index: 82377 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1005. Min Range: -6.1005
Max Act: 5.9130. Min Act: -0.1700
Data Index: 488499 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1005. Min Range: -6.1005
Max Act: 5.9130. Min Act: -0.1700
Data Index: 1119127 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1005. Min Range: -6.1005
Max Act: 5.9130. Min Act: -0.1700
Data Index: 7705326 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1005. Min Range: -6.1005
Max Act: 5.9130. Min Act: -0.1700
Data Index: 4183741 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1005. Min Range: -6.1005
Max Act: 5.8818. Min Act: -0.1700
Data Index: 299141 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1005. Min Range: -6.1005
Max Act: 5.9130. Min Act: -0.1700
Data Index: 1583793 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1005. Min Range: -6.1005
Max Act: 5.8818. Min Act: -0.1700
Data Index: 7825552 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1005. Min Range: -6.1005
Max Act: 5.8818. Min Act: -0.1700
Data Index: 4352527 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1005. Min Range: -6.1005
Max Act: 5.8818. Min Act: -0.1700
Data Index: 7584227 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1005. Min Range: -6.1005
Max Act: 5.8505. Min Act: -0.1700
Data Index: 7521492 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1005. Min Range: -6.1005
Max Act: 5.8818. Min Act: -0.1700
Data Index: 7016364 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1005. Min Range: -6.1005
Max Act: 5.8818. Min Act: -0.1700
Data Index: 6632974 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1005. Min Range: -6.1005
Max Act: 5.8505. Min Act: -0.1700
Data Index: 4556464 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #19