Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2940 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8025. Min Range: -2.8025
Max Act: 2.8025. Min Act: -0.1700
Data Index: 6018050 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8025. Min Range: -2.8025
Max Act: 2.7866. Min Act: -0.1700
Data Index: 5978133 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8025. Min Range: -2.8025
Max Act: 2.7547. Min Act: -0.1700
Data Index: 1284805 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8025. Min Range: -2.8025
Max Act: 2.7228. Min Act: -0.1700
Data Index: 2099570 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8025. Min Range: -2.8025
Max Act: 2.7068. Min Act: -0.1700
Data Index: 3739414 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8025. Min Range: -2.8025
Max Act: 2.7068. Min Act: -0.1700
Data Index: 3770019 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8025. Min Range: -2.8025
Max Act: 2.7068. Min Act: -0.1700
Data Index: 4482791 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8025. Min Range: -2.8025
Max Act: 2.6908. Min Act: -0.1700
Data Index: 4970457 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8025. Min Range: -2.8025
Max Act: 2.6747. Min Act: -0.1700
Data Index: 2389416 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8025. Min Range: -2.8025
Max Act: 2.6427. Min Act: -0.1700
Data Index: 4993029 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8025. Min Range: -2.8025
Max Act: 2.6587. Min Act: -0.1700
Data Index: 6925277 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8025. Min Range: -2.8025
Max Act: 2.6587. Min Act: -0.1700
Data Index: 2339790 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8025. Min Range: -2.8025
Max Act: 2.6747. Min Act: -0.1700
Data Index: 6018059 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8025. Min Range: -2.8025
Max Act: 2.6587. Min Act: -0.1700
Data Index: 24796 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8025. Min Range: -2.8025
Max Act: 2.6427. Min Act: -0.1700
Data Index: 8020293 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8025. Min Range: -2.8025
Max Act: 2.6427. Min Act: -0.1700
Data Index: 6646278 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8025. Min Range: -2.8025
Max Act: 2.6266. Min Act: -0.1700
Data Index: 8469119 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8025. Min Range: -2.8025
Max Act: 2.6266. Min Act: -0.1700
Data Index: 1057888 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8025. Min Range: -2.8025
Max Act: 2.6427. Min Act: -0.1700
Data Index: 6150052 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8025. Min Range: -2.8025
Max Act: 2.6427. Min Act: -0.1700
Data Index: 7876310 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #19