Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4014 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7058. Min Range: -4.7058
Max Act: 4.7058. Min Act: -0.1700
Data Index: 4065191 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7058. Min Range: -4.7058
Max Act: 4.6433. Min Act: -0.1700
Data Index: 196353 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7058. Min Range: -4.7058
Max Act: 4.5808. Min Act: -0.1700
Data Index: 4065192 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7058. Min Range: -4.7058
Max Act: 4.5495. Min Act: -0.1700
Data Index: 1966530 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7058. Min Range: -4.7058
Max Act: 4.5183. Min Act: -0.1700
Data Index: 3004521 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7058. Min Range: -4.7058
Max Act: 4.5183. Min Act: -0.1700
Data Index: 478994 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7058. Min Range: -4.7058
Max Act: 4.4870. Min Act: -0.1700
Data Index: 7625936 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7058. Min Range: -4.7058
Max Act: 4.4870. Min Act: -0.1700
Data Index: 932454 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7058. Min Range: -4.7058
Max Act: 4.4558. Min Act: -0.1700
Data Index: 2796761 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7058. Min Range: -4.7058
Max Act: 4.4558. Min Act: -0.1700
Data Index: 2417205 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7058. Min Range: -4.7058
Max Act: 4.4558. Min Act: -0.1700
Data Index: 665792 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7058. Min Range: -4.7058
Max Act: 4.4558. Min Act: -0.1700
Data Index: 7298005 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7058. Min Range: -4.7058
Max Act: 4.4870. Min Act: -0.1700
Data Index: 8699570 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7058. Min Range: -4.7058
Max Act: 4.4558. Min Act: -0.1700
Data Index: 7675734 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7058. Min Range: -4.7058
Max Act: 4.4245. Min Act: -0.1700
Data Index: 328127 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7058. Min Range: -4.7058
Max Act: 4.4245. Min Act: -0.1700
Data Index: 7035240 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7058. Min Range: -4.7058
Max Act: 4.4245. Min Act: -0.1700
Data Index: 3329179 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7058. Min Range: -4.7058
Max Act: 4.4245. Min Act: -0.1700
Data Index: 4162098 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7058. Min Range: -4.7058
Max Act: 4.4245. Min Act: -0.1700
Data Index: 2551734 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7058. Min Range: -4.7058
Max Act: 4.4245. Min Act: -0.1700
Data Index: 7143982 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #19