Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2573 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9305. Min Range: -6.9305
Max Act: 6.9305. Min Act: -0.1700
Data Index: 152925 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9305. Min Range: -6.9305
Max Act: 6.9305. Min Act: -0.1700
Data Index: 1065186 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9305. Min Range: -6.9305
Max Act: 6.8680. Min Act: -0.1700
Data Index: 1879287 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9305. Min Range: -6.9305
Max Act: 6.7118. Min Act: -0.1700
Data Index: 7049026 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9305. Min Range: -6.9305
Max Act: 6.6805. Min Act: -0.1700
Data Index: 1133161 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9305. Min Range: -6.9305
Max Act: 6.6180. Min Act: -0.1700
Data Index: 6871484 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9305. Min Range: -6.9305
Max Act: 6.6180. Min Act: -0.1700
Data Index: 5403372 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9305. Min Range: -6.9305
Max Act: 6.6180. Min Act: -0.1700
Data Index: 3658813 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9305. Min Range: -6.9305
Max Act: 6.7118. Min Act: -0.1700
Data Index: 3233451 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9305. Min Range: -6.9305
Max Act: 6.6180. Min Act: -0.1700
Data Index: 2562687 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9305. Min Range: -6.9305
Max Act: 6.5868. Min Act: -0.1700
Data Index: 2668059 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9305. Min Range: -6.9305
Max Act: 6.5868. Min Act: -0.1700
Data Index: 376729 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9305. Min Range: -6.9305
Max Act: 6.5868. Min Act: -0.1700
Data Index: 7114454 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9305. Min Range: -6.9305
Max Act: 6.5243. Min Act: -0.1700
Data Index: 1364242 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9305. Min Range: -6.9305
Max Act: 6.6180. Min Act: -0.1700
Data Index: 5568704 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9305. Min Range: -6.9305
Max Act: 6.5243. Min Act: -0.1700
Data Index: 5261957 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9305. Min Range: -6.9305
Max Act: 6.5243. Min Act: -0.1700
Data Index: 5677627 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9305. Min Range: -6.9305
Max Act: 6.5243. Min Act: -0.1700
Data Index: 4870092 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9305. Min Range: -6.9305
Max Act: 6.4930. Min Act: -0.1700
Data Index: 2163589 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9305. Min Range: -6.9305
Max Act: 6.5243. Min Act: -0.1700
Data Index: 6551263 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #19