Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 21 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.5801. Min Act: -0.1700
Data Index: 7846477 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.3926. Min Act: -0.1700
Data Index: 3037504 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.3926. Min Act: -0.1700
Data Index: 1689607 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.2988. Min Act: -0.1700
Data Index: 1897306 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.2676. Min Act: -0.1700
Data Index: 1689606 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.2988. Min Act: -0.1700
Data Index: 4970491 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.2363. Min Act: -0.1700
Data Index: 3882095 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.2363. Min Act: -0.1700
Data Index: 7895448 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.2051. Min Act: -0.1700
Data Index: 1689602 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.2051. Min Act: -0.1700
Data Index: 5119692 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.1426. Min Act: -0.1700
Data Index: 1280042 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.1113. Min Act: -0.1700
Data Index: 2187544 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.1113. Min Act: -0.1700
Data Index: 7670742 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.0801. Min Act: -0.1700
Data Index: 5107339 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.0801. Min Act: -0.1700
Data Index: 4385335 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.0801. Min Act: -0.1700
Data Index: 5454408 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.0801. Min Act: -0.1700
Data Index: 6122742 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.0801. Min Act: -0.1700
Data Index: 7322333 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.0488. Min Act: -0.1700
Data Index: 1663013 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.0801. Min Act: -0.1700
Data Index: 3729873 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #19