Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 610 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.5134. Min Act: -0.1700
Data Index: 4383548 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.4196. Min Act: -0.1700
Data Index: 6132764 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.3884. Min Act: -0.1700
Data Index: 7141738 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.3884. Min Act: -0.1700
Data Index: 7022889 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.3571. Min Act: -0.1700
Data Index: 2632250 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.3571. Min Act: -0.1700
Data Index: 7510949 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.3571. Min Act: -0.1700
Data Index: 3652714 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.3571. Min Act: -0.1700
Data Index: 1581119 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.3259. Min Act: -0.1700
Data Index: 2889236 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.3259. Min Act: -0.1700
Data Index: 1884472 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.3259. Min Act: -0.1700
Data Index: 6179685 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.3259. Min Act: -0.1700
Data Index: 5543247 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.3259. Min Act: -0.1700
Data Index: 5106347 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.3259. Min Act: -0.1700
Data Index: 193971 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.3259. Min Act: -0.1700
Data Index: 4932704 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.3259. Min Act: -0.1700
Data Index: 1115091 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.3259. Min Act: -0.1700
Data Index: 750126 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.3259. Min Act: -0.1700
Data Index: 3350759 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.2946. Min Act: -0.1700
Data Index: 50228 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.2946. Min Act: -0.1700
Data Index: 2199608 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #19