Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 80 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8249. Min Range: -5.8249
Max Act: 5.8249. Min Act: -0.1700
Data Index: 7318346 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8249. Min Range: -5.8249
Max Act: 5.7937. Min Act: -0.1700
Data Index: 5834501 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8249. Min Range: -5.8249
Max Act: 5.7624. Min Act: -0.1700
Data Index: 4139770 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8249. Min Range: -5.8249
Max Act: 5.7937. Min Act: -0.1700
Data Index: 5518938 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8249. Min Range: -5.8249
Max Act: 5.7624. Min Act: -0.1700
Data Index: 5954702 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8249. Min Range: -5.8249
Max Act: 5.6999. Min Act: -0.1700
Data Index: 7088622 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8249. Min Range: -5.8249
Max Act: 5.6999. Min Act: -0.1700
Data Index: 8627829 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8249. Min Range: -5.8249
Max Act: 5.6999. Min Act: -0.1700
Data Index: 8270898 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8249. Min Range: -5.8249
Max Act: 5.6687. Min Act: -0.1700
Data Index: 1854468 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8249. Min Range: -5.8249
Max Act: 5.6374. Min Act: -0.1700
Data Index: 5954703 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8249. Min Range: -5.8249
Max Act: 5.6374. Min Act: -0.1700
Data Index: 7888845 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8249. Min Range: -5.8249
Max Act: 5.5749. Min Act: -0.1700
Data Index: 291293 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8249. Min Range: -5.8249
Max Act: 5.6062. Min Act: -0.1700
Data Index: 2855364 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8249. Min Range: -5.8249
Max Act: 5.5437. Min Act: -0.1700
Data Index: 8270888 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8249. Min Range: -5.8249
Max Act: 5.5749. Min Act: -0.1700
Data Index: 2808697 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8249. Min Range: -5.8249
Max Act: 5.5124. Min Act: -0.1700
Data Index: 830900 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8249. Min Range: -5.8249
Max Act: 5.5124. Min Act: -0.1700
Data Index: 6602819 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8249. Min Range: -5.8249
Max Act: 5.5749. Min Act: -0.1700
Data Index: 551547 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8249. Min Range: -5.8249
Max Act: 5.5437. Min Act: -0.1700
Data Index: 2953433 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8249. Min Range: -5.8249
Max Act: 5.5437. Min Act: -0.1700
Data Index: 5971460 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #19