Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2905 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7438. Min Range: -3.7438
Max Act: 3.7438. Min Act: -0.1700
Data Index: 220995 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7438. Min Range: -3.7438
Max Act: 3.6969. Min Act: -0.1700
Data Index: 3016050 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7438. Min Range: -3.7438
Max Act: 3.5717. Min Act: -0.1700
Data Index: 206358 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7438. Min Range: -3.7438
Max Act: 3.5091. Min Act: -0.1700
Data Index: 4828815 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7438. Min Range: -3.7438
Max Act: 3.4934. Min Act: -0.1700
Data Index: 3480376 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7438. Min Range: -3.7438
Max Act: 3.4934. Min Act: -0.1700
Data Index: 1920909 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7438. Min Range: -3.7438
Max Act: 3.4307. Min Act: -0.1700
Data Index: 7136452 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7438. Min Range: -3.7438
Max Act: 3.4307. Min Act: -0.1700
Data Index: 8484341 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7438. Min Range: -3.7438
Max Act: 3.4151. Min Act: -0.1700
Data Index: 300965 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7438. Min Range: -3.7438
Max Act: 3.4151. Min Act: -0.1700
Data Index: 6612657 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7438. Min Range: -3.7438
Max Act: 3.3994. Min Act: -0.1700
Data Index: 5665446 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7438. Min Range: -3.7438
Max Act: 3.3994. Min Act: -0.1700
Data Index: 6912167 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7438. Min Range: -3.7438
Max Act: 3.3994. Min Act: -0.1700
Data Index: 4656261 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7438. Min Range: -3.7438
Max Act: 3.3837. Min Act: -0.1700
Data Index: 430799 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7438. Min Range: -3.7438
Max Act: 3.3680. Min Act: -0.1700
Data Index: 4162948 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7438. Min Range: -3.7438
Max Act: 3.3837. Min Act: -0.1700
Data Index: 4404220 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7438. Min Range: -3.7438
Max Act: 3.3680. Min Act: -0.1700
Data Index: 2778468 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7438. Min Range: -3.7438
Max Act: 3.3680. Min Act: -0.1700
Data Index: 6406064 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7438. Min Range: -3.7438
Max Act: 3.3366. Min Act: -0.1700
Data Index: 1540528 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7438. Min Range: -3.7438
Max Act: 3.3366. Min Act: -0.1700
Data Index: 256912 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #19