Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1144 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 12.3453. Min Range: -12.3453
Max Act: 12.3453. Min Act: -0.1700
Data Index: 3484026 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.3453. Min Range: -12.3453
Max Act: 11.9703. Min Act: -0.1700
Data Index: 7809427 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.3453. Min Range: -12.3453
Max Act: 11.5328. Min Act: -0.1700
Data Index: 2035157 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.3453. Min Range: -12.3453
Max Act: 11.5328. Min Act: -0.1700
Data Index: 6340100 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.3453. Min Range: -12.3453
Max Act: 11.4703. Min Act: -0.1700
Data Index: 4903464 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.3453. Min Range: -12.3453
Max Act: 11.4703. Min Act: -0.1700
Data Index: 7988309 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.3453. Min Range: -12.3453
Max Act: 11.4703. Min Act: -0.1700
Data Index: 960666 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.3453. Min Range: -12.3453
Max Act: 11.4703. Min Act: -0.1700
Data Index: 4439992 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.3453. Min Range: -12.3453
Max Act: 11.4078. Min Act: -0.1700
Data Index: 2785572 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.3453. Min Range: -12.3453
Max Act: 11.4078. Min Act: -0.1700
Data Index: 130297 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.3453. Min Range: -12.3453
Max Act: 11.4078. Min Act: -0.1700
Data Index: 8564598 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.3453. Min Range: -12.3453
Max Act: 11.2828. Min Act: -0.1700
Data Index: 8499359 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.3453. Min Range: -12.3453
Max Act: 11.4078. Min Act: -0.1700
Data Index: 4116465 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.3453. Min Range: -12.3453
Max Act: 11.2828. Min Act: -0.1700
Data Index: 2103114 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.3453. Min Range: -12.3453
Max Act: 11.1578. Min Act: -0.1700
Data Index: 5507683 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.3453. Min Range: -12.3453
Max Act: 11.0953. Min Act: -0.1700
Data Index: 8315048 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.3453. Min Range: -12.3453
Max Act: 11.2203. Min Act: -0.1700
Data Index: 8475250 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.3453. Min Range: -12.3453
Max Act: 11.1578. Min Act: -0.1700
Data Index: 503440 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.3453. Min Range: -12.3453
Max Act: 11.0953. Min Act: -0.1700
Data Index: 7668903 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.3453. Min Range: -12.3453
Max Act: 11.0953. Min Act: -0.1700
Data Index: 7817011 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #19