Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2574 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9047. Min Range: -6.9047
Max Act: 6.9047. Min Act: -0.1700
Data Index: 8506190 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9047. Min Range: -6.9047
Max Act: 6.8735. Min Act: -0.1700
Data Index: 7005087 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9047. Min Range: -6.9047
Max Act: 6.8422. Min Act: -0.1700
Data Index: 4601190 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9047. Min Range: -6.9047
Max Act: 6.7797. Min Act: -0.1700
Data Index: 7005086 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9047. Min Range: -6.9047
Max Act: 6.7485. Min Act: -0.1700
Data Index: 3979005 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9047. Min Range: -6.9047
Max Act: 6.7797. Min Act: -0.1700
Data Index: 307035 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9047. Min Range: -6.9047
Max Act: 6.7485. Min Act: -0.1700
Data Index: 8357704 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9047. Min Range: -6.9047
Max Act: 6.7485. Min Act: -0.1700
Data Index: 2548450 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9047. Min Range: -6.9047
Max Act: 6.7172. Min Act: -0.1700
Data Index: 1312251 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9047. Min Range: -6.9047
Max Act: 6.7172. Min Act: -0.1700
Data Index: 20430 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9047. Min Range: -6.9047
Max Act: 6.7485. Min Act: -0.1700
Data Index: 1677073 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9047. Min Range: -6.9047
Max Act: 6.7172. Min Act: -0.1700
Data Index: 7952639 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9047. Min Range: -6.9047
Max Act: 6.6547. Min Act: -0.1700
Data Index: 2744467 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9047. Min Range: -6.9047
Max Act: 6.6547. Min Act: -0.1700
Data Index: 3151205 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9047. Min Range: -6.9047
Max Act: 6.6235. Min Act: -0.1700
Data Index: 7144453 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9047. Min Range: -6.9047
Max Act: 6.5610. Min Act: -0.1700
Data Index: 3570472 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9047. Min Range: -6.9047
Max Act: 6.5297. Min Act: -0.1700
Data Index: 1677072 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9047. Min Range: -6.9047
Max Act: 6.5297. Min Act: -0.1700
Data Index: 4247688 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9047. Min Range: -6.9047
Max Act: 6.4985. Min Act: -0.1700
Data Index: 4437716 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9047. Min Range: -6.9047
Max Act: 6.4985. Min Act: -0.1700
Data Index: 1389440 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #19