Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 474 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0769. Min Range: -5.0769
Max Act: 5.0769. Min Act: -0.1700
Data Index: 3837987 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0769. Min Range: -5.0769
Max Act: 5.0144. Min Act: -0.1700
Data Index: 2860480 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0769. Min Range: -5.0769
Max Act: 4.9519. Min Act: -0.1700
Data Index: 8807137 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0769. Min Range: -5.0769
Max Act: 4.9206. Min Act: -0.1700
Data Index: 802154 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0769. Min Range: -5.0769
Max Act: 4.9206. Min Act: -0.1700
Data Index: 1722353 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0769. Min Range: -5.0769
Max Act: 4.9206. Min Act: -0.1700
Data Index: 3362439 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0769. Min Range: -5.0769
Max Act: 4.9206. Min Act: -0.1700
Data Index: 6751342 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0769. Min Range: -5.0769
Max Act: 4.8894. Min Act: -0.1700
Data Index: 8624935 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0769. Min Range: -5.0769
Max Act: 4.9206. Min Act: -0.1700
Data Index: 7503108 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0769. Min Range: -5.0769
Max Act: 4.9206. Min Act: -0.1700
Data Index: 3594209 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0769. Min Range: -5.0769
Max Act: 4.8581. Min Act: -0.1700
Data Index: 4076411 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0769. Min Range: -5.0769
Max Act: 4.8581. Min Act: -0.1700
Data Index: 8149090 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0769. Min Range: -5.0769
Max Act: 4.8581. Min Act: -0.1700
Data Index: 656212 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0769. Min Range: -5.0769
Max Act: 4.8581. Min Act: -0.1700
Data Index: 5254676 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0769. Min Range: -5.0769
Max Act: 4.7956. Min Act: -0.1700
Data Index: 2537725 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0769. Min Range: -5.0769
Max Act: 4.7956. Min Act: -0.1700
Data Index: 418787 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0769. Min Range: -5.0769
Max Act: 4.8269. Min Act: -0.1700
Data Index: 848899 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0769. Min Range: -5.0769
Max Act: 4.8269. Min Act: -0.1700
Data Index: 8620001 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0769. Min Range: -5.0769
Max Act: 4.8269. Min Act: -0.1700
Data Index: 6330929 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0769. Min Range: -5.0769
Max Act: 4.8581. Min Act: -0.1700
Data Index: 4072093 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #19