Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3322 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0062. Min Range: -5.0062
Max Act: 5.0062. Min Act: -0.1700
Data Index: 3112382 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0062. Min Range: -5.0062
Max Act: 4.8812. Min Act: -0.1700
Data Index: 7624238 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0062. Min Range: -5.0062
Max Act: 4.6937. Min Act: -0.1700
Data Index: 6300228 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0062. Min Range: -5.0062
Max Act: 4.7249. Min Act: -0.1700
Data Index: 6078714 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0062. Min Range: -5.0062
Max Act: 4.6312. Min Act: -0.1700
Data Index: 2295429 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0062. Min Range: -5.0062
Max Act: 4.5999. Min Act: -0.1700
Data Index: 5216275 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0062. Min Range: -5.0062
Max Act: 4.5687. Min Act: -0.1700
Data Index: 7785274 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0062. Min Range: -5.0062
Max Act: 4.5374. Min Act: -0.1700
Data Index: 7109174 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0062. Min Range: -5.0062
Max Act: 4.5374. Min Act: -0.1700
Data Index: 7795760 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0062. Min Range: -5.0062
Max Act: 4.5374. Min Act: -0.1700
Data Index: 4218116 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0062. Min Range: -5.0062
Max Act: 4.5374. Min Act: -0.1700
Data Index: 2375469 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0062. Min Range: -5.0062
Max Act: 4.5374. Min Act: -0.1700
Data Index: 3270152 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0062. Min Range: -5.0062
Max Act: 4.5374. Min Act: -0.1700
Data Index: 1733166 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0062. Min Range: -5.0062
Max Act: 4.5374. Min Act: -0.1700
Data Index: 3012355 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0062. Min Range: -5.0062
Max Act: 4.5062. Min Act: -0.1700
Data Index: 6946436 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0062. Min Range: -5.0062
Max Act: 4.5062. Min Act: -0.1700
Data Index: 6926438 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0062. Min Range: -5.0062
Max Act: 4.5062. Min Act: -0.1700
Data Index: 6825783 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0062. Min Range: -5.0062
Max Act: 4.5062. Min Act: -0.1700
Data Index: 6080163 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0062. Min Range: -5.0062
Max Act: 4.5062. Min Act: -0.1700
Data Index: 3749769 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0062. Min Range: -5.0062
Max Act: 4.5062. Min Act: -0.1700
Data Index: 6386012 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #19