Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2928 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9155. Min Range: -2.9155
Max Act: 2.9155. Min Act: -0.1700
Data Index: 1092925 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9155. Min Range: -2.9155
Max Act: 2.8361. Min Act: -0.1700
Data Index: 3893674 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9155. Min Range: -2.9155
Max Act: 2.8361. Min Act: -0.1700
Data Index: 77819 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9155. Min Range: -2.9155
Max Act: 2.7884. Min Act: -0.1700
Data Index: 7472756 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9155. Min Range: -2.9155
Max Act: 2.7724. Min Act: -0.1700
Data Index: 2668417 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9155. Min Range: -2.9155
Max Act: 2.7405. Min Act: -0.1700
Data Index: 2753880 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9155. Min Range: -2.9155
Max Act: 2.7245. Min Act: -0.1700
Data Index: 2624493 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9155. Min Range: -2.9155
Max Act: 2.7085. Min Act: -0.1700
Data Index: 299383 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9155. Min Range: -2.9155
Max Act: 2.6765. Min Act: -0.1700
Data Index: 360455 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9155. Min Range: -2.9155
Max Act: 2.6765. Min Act: -0.1700
Data Index: 4166893 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9155. Min Range: -2.9155
Max Act: 2.6925. Min Act: -0.1700
Data Index: 41596 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9155. Min Range: -2.9155
Max Act: 2.6765. Min Act: -0.1700
Data Index: 7727341 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9155. Min Range: -2.9155
Max Act: 2.6925. Min Act: -0.1700
Data Index: 8407864 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9155. Min Range: -2.9155
Max Act: 2.6925. Min Act: -0.1700
Data Index: 5229814 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9155. Min Range: -2.9155
Max Act: 2.6765. Min Act: -0.1700
Data Index: 2084340 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9155. Min Range: -2.9155
Max Act: 2.6605. Min Act: -0.1700
Data Index: 4802398 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9155. Min Range: -2.9155
Max Act: 2.6765. Min Act: -0.1700
Data Index: 8654459 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9155. Min Range: -2.9155
Max Act: 2.6765. Min Act: -0.1700
Data Index: 7783273 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9155. Min Range: -2.9155
Max Act: 2.6765. Min Act: -0.1700
Data Index: 7809351 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9155. Min Range: -2.9155
Max Act: 2.6445. Min Act: -0.1700
Data Index: 6762304 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #19