Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 317 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.1075. Min Range: -8.1075
Max Act: 8.1075. Min Act: -0.1700
Data Index: 2376732 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1075. Min Range: -8.1075
Max Act: 7.9825. Min Act: -0.1700
Data Index: 5681882 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1075. Min Range: -8.1075
Max Act: 7.8262. Min Act: -0.1700
Data Index: 4879775 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1075. Min Range: -8.1075
Max Act: 7.7637. Min Act: -0.1700
Data Index: 15946 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1075. Min Range: -8.1075
Max Act: 7.7325. Min Act: -0.1700
Data Index: 1925453 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1075. Min Range: -8.1075
Max Act: 7.6700. Min Act: -0.1700
Data Index: 27431 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1075. Min Range: -8.1075
Max Act: 7.6700. Min Act: -0.1700
Data Index: 8234636 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1075. Min Range: -8.1075
Max Act: 7.6075. Min Act: -0.1700
Data Index: 8573733 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1075. Min Range: -8.1075
Max Act: 7.5450. Min Act: -0.1700
Data Index: 213168 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1075. Min Range: -8.1075
Max Act: 7.5450. Min Act: -0.1700
Data Index: 7882716 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1075. Min Range: -8.1075
Max Act: 7.5137. Min Act: -0.1700
Data Index: 7315794 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1075. Min Range: -8.1075
Max Act: 7.4825. Min Act: -0.1700
Data Index: 7821237 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1075. Min Range: -8.1075
Max Act: 7.4825. Min Act: -0.1700
Data Index: 1159569 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1075. Min Range: -8.1075
Max Act: 7.5137. Min Act: -0.1700
Data Index: 8208408 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1075. Min Range: -8.1075
Max Act: 7.4825. Min Act: -0.1700
Data Index: 2840462 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1075. Min Range: -8.1075
Max Act: 7.5137. Min Act: -0.1700
Data Index: 1243117 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1075. Min Range: -8.1075
Max Act: 7.4512. Min Act: -0.1700
Data Index: 5714822 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1075. Min Range: -8.1075
Max Act: 7.4512. Min Act: -0.1700
Data Index: 6290132 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1075. Min Range: -8.1075
Max Act: 7.4512. Min Act: -0.1700
Data Index: 756878 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1075. Min Range: -8.1075
Max Act: 7.4200. Min Act: -0.1700
Data Index: 3021226 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #19