Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2802 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9753. Min Range: -5.9753
Max Act: 5.9753. Min Act: -0.1700
Data Index: 6285467 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9753. Min Range: -5.9753
Max Act: 5.5066. Min Act: -0.1700
Data Index: 4289705 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9753. Min Range: -5.9753
Max Act: 5.5066. Min Act: -0.1700
Data Index: 7164227 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9753. Min Range: -5.9753
Max Act: 5.5066. Min Act: -0.1700
Data Index: 5328517 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9753. Min Range: -5.9753
Max Act: 5.4753. Min Act: -0.1700
Data Index: 3768153 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9753. Min Range: -5.9753
Max Act: 5.4753. Min Act: -0.1700
Data Index: 8499171 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9753. Min Range: -5.9753
Max Act: 5.4128. Min Act: -0.1700
Data Index: 2723384 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9753. Min Range: -5.9753
Max Act: 5.4441. Min Act: -0.1700
Data Index: 707301 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9753. Min Range: -5.9753
Max Act: 5.3816. Min Act: -0.1700
Data Index: 67997 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9753. Min Range: -5.9753
Max Act: 5.3816. Min Act: -0.1700
Data Index: 1984477 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9753. Min Range: -5.9753
Max Act: 5.3503. Min Act: -0.1700
Data Index: 6759869 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9753. Min Range: -5.9753
Max Act: 5.3191. Min Act: -0.1700
Data Index: 140464 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9753. Min Range: -5.9753
Max Act: 5.3503. Min Act: -0.1700
Data Index: 3921722 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9753. Min Range: -5.9753
Max Act: 5.3503. Min Act: -0.1700
Data Index: 1920723 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9753. Min Range: -5.9753
Max Act: 5.3191. Min Act: -0.1700
Data Index: 4874408 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9753. Min Range: -5.9753
Max Act: 5.3191. Min Act: -0.1700
Data Index: 1293930 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9753. Min Range: -5.9753
Max Act: 5.3503. Min Act: -0.1700
Data Index: 4926711 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9753. Min Range: -5.9753
Max Act: 5.3503. Min Act: -0.1700
Data Index: 6141055 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9753. Min Range: -5.9753
Max Act: 5.3503. Min Act: -0.1700
Data Index: 407447 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9753. Min Range: -5.9753
Max Act: 5.2878. Min Act: -0.1700
Data Index: 969188 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #19