Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1751 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8648. Min Range: -9.8648
Max Act: 9.8648. Min Act: -0.1700
Data Index: 218859 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8648. Min Range: -9.8648
Max Act: 9.4898. Min Act: -0.1700
Data Index: 5010230 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8648. Min Range: -9.8648
Max Act: 9.5523. Min Act: -0.1700
Data Index: 2310207 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8648. Min Range: -9.8648
Max Act: 9.4898. Min Act: -0.1700
Data Index: 2352326 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8648. Min Range: -9.8648
Max Act: 9.4273. Min Act: -0.1700
Data Index: 7472827 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8648. Min Range: -9.8648
Max Act: 9.4273. Min Act: -0.1700
Data Index: 2494000 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8648. Min Range: -9.8648
Max Act: 9.3023. Min Act: -0.1700
Data Index: 1594983 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8648. Min Range: -9.8648
Max Act: 9.3648. Min Act: -0.1700
Data Index: 1668072 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8648. Min Range: -9.8648
Max Act: 9.4273. Min Act: -0.1700
Data Index: 129923 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8648. Min Range: -9.8648
Max Act: 9.3648. Min Act: -0.1700
Data Index: 5813397 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8648. Min Range: -9.8648
Max Act: 9.3648. Min Act: -0.1700
Data Index: 4657855 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8648. Min Range: -9.8648
Max Act: 9.3023. Min Act: -0.1700
Data Index: 1637175 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8648. Min Range: -9.8648
Max Act: 9.2398. Min Act: -0.1700
Data Index: 6421211 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8648. Min Range: -9.8648
Max Act: 9.1773. Min Act: -0.1700
Data Index: 790486 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8648. Min Range: -9.8648
Max Act: 9.1773. Min Act: -0.1700
Data Index: 1546155 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8648. Min Range: -9.8648
Max Act: 9.1148. Min Act: -0.1700
Data Index: 1576949 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8648. Min Range: -9.8648
Max Act: 9.1148. Min Act: -0.1700
Data Index: 3387064 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8648. Min Range: -9.8648
Max Act: 9.1148. Min Act: -0.1700
Data Index: 5277702 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8648. Min Range: -9.8648
Max Act: 9.0523. Min Act: -0.1700
Data Index: 6675555 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8648. Min Range: -9.8648
Max Act: 9.1148. Min Act: -0.1700
Data Index: 3035113 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #19