Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2833 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5683. Min Range: -4.5683
Max Act: 4.5683. Min Act: -0.1700
Data Index: 2155205 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5683. Min Range: -4.5683
Max Act: 4.4432. Min Act: -0.1700
Data Index: 7078612 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5683. Min Range: -4.5683
Max Act: 4.4745. Min Act: -0.1700
Data Index: 755869 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5683. Min Range: -4.5683
Max Act: 4.4745. Min Act: -0.1700
Data Index: 4184059 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5683. Min Range: -4.5683
Max Act: 4.4745. Min Act: -0.1700
Data Index: 2691911 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5683. Min Range: -4.5683
Max Act: 4.4120. Min Act: -0.1700
Data Index: 3799630 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5683. Min Range: -4.5683
Max Act: 4.4120. Min Act: -0.1700
Data Index: 5159238 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5683. Min Range: -4.5683
Max Act: 4.4120. Min Act: -0.1700
Data Index: 5388644 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5683. Min Range: -4.5683
Max Act: 4.4120. Min Act: -0.1700
Data Index: 310238 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5683. Min Range: -4.5683
Max Act: 4.3807. Min Act: -0.1700
Data Index: 2788865 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5683. Min Range: -4.5683
Max Act: 4.4120. Min Act: -0.1700
Data Index: 270631 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5683. Min Range: -4.5683
Max Act: 4.4120. Min Act: -0.1700
Data Index: 4581881 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5683. Min Range: -4.5683
Max Act: 4.3807. Min Act: -0.1700
Data Index: 1314187 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5683. Min Range: -4.5683
Max Act: 4.3807. Min Act: -0.1700
Data Index: 1607277 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5683. Min Range: -4.5683
Max Act: 4.3807. Min Act: -0.1700
Data Index: 4746941 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5683. Min Range: -4.5683
Max Act: 4.3807. Min Act: -0.1700
Data Index: 3273335 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5683. Min Range: -4.5683
Max Act: 4.3807. Min Act: -0.1700
Data Index: 2920148 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5683. Min Range: -4.5683
Max Act: 4.4120. Min Act: -0.1700
Data Index: 459560 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5683. Min Range: -4.5683
Max Act: 4.3807. Min Act: -0.1700
Data Index: 6062893 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5683. Min Range: -4.5683
Max Act: 4.3495. Min Act: -0.1700
Data Index: 809687 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #19