Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1235 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7119. Min Range: -7.7119
Max Act: 7.7119. Min Act: -0.1700
Data Index: 4948033 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7119. Min Range: -7.7119
Max Act: 7.5556. Min Act: -0.1700
Data Index: 1154326 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7119. Min Range: -7.7119
Max Act: 7.3681. Min Act: -0.1700
Data Index: 8129786 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7119. Min Range: -7.7119
Max Act: 7.3056. Min Act: -0.1700
Data Index: 1393206 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7119. Min Range: -7.7119
Max Act: 7.3369. Min Act: -0.1700
Data Index: 505838 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7119. Min Range: -7.7119
Max Act: 7.2744. Min Act: -0.1700
Data Index: 8770226 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7119. Min Range: -7.7119
Max Act: 7.2744. Min Act: -0.1700
Data Index: 4376848 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7119. Min Range: -7.7119
Max Act: 7.2431. Min Act: -0.1700
Data Index: 8802996 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7119. Min Range: -7.7119
Max Act: 7.2119. Min Act: -0.1700
Data Index: 8705906 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7119. Min Range: -7.7119
Max Act: 7.2119. Min Act: -0.1700
Data Index: 6381935 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7119. Min Range: -7.7119
Max Act: 7.1806. Min Act: -0.1700
Data Index: 71876 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7119. Min Range: -7.7119
Max Act: 7.1494. Min Act: -0.1700
Data Index: 7417189 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7119. Min Range: -7.7119
Max Act: 7.1806. Min Act: -0.1700
Data Index: 4137738 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7119. Min Range: -7.7119
Max Act: 7.1494. Min Act: -0.1700
Data Index: 4099813 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7119. Min Range: -7.7119
Max Act: 7.1181. Min Act: -0.1700
Data Index: 1119551 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7119. Min Range: -7.7119
Max Act: 7.1181. Min Act: -0.1700
Data Index: 618896 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7119. Min Range: -7.7119
Max Act: 7.1181. Min Act: -0.1700
Data Index: 6860994 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7119. Min Range: -7.7119
Max Act: 7.1181. Min Act: -0.1700
Data Index: 129641 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7119. Min Range: -7.7119
Max Act: 7.0869. Min Act: -0.1700
Data Index: 2441303 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7119. Min Range: -7.7119
Max Act: 7.0556. Min Act: -0.1700
Data Index: 6537390 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #19