Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 39 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0562. Min Range: -5.0562
Max Act: 5.0562. Min Act: -0.1700
Data Index: 8787373 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0562. Min Range: -5.0562
Max Act: 5.0249. Min Act: -0.1700
Data Index: 3833078 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0562. Min Range: -5.0562
Max Act: 5.0249. Min Act: -0.1700
Data Index: 2351642 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0562. Min Range: -5.0562
Max Act: 4.9312. Min Act: -0.1700
Data Index: 5656818 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0562. Min Range: -5.0562
Max Act: 4.9312. Min Act: -0.1700
Data Index: 3823308 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0562. Min Range: -5.0562
Max Act: 4.9624. Min Act: -0.1700
Data Index: 246624 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0562. Min Range: -5.0562
Max Act: 4.8999. Min Act: -0.1700
Data Index: 8319896 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0562. Min Range: -5.0562
Max Act: 4.9312. Min Act: -0.1700
Data Index: 8643023 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0562. Min Range: -5.0562
Max Act: 4.9312. Min Act: -0.1700
Data Index: 283920 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0562. Min Range: -5.0562
Max Act: 4.8687. Min Act: -0.1700
Data Index: 8492260 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0562. Min Range: -5.0562
Max Act: 4.8374. Min Act: -0.1700
Data Index: 6803862 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0562. Min Range: -5.0562
Max Act: 4.8374. Min Act: -0.1700
Data Index: 1959261 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0562. Min Range: -5.0562
Max Act: 4.8062. Min Act: -0.1700
Data Index: 1196111 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0562. Min Range: -5.0562
Max Act: 4.8687. Min Act: -0.1700
Data Index: 6886545 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0562. Min Range: -5.0562
Max Act: 4.8062. Min Act: -0.1700
Data Index: 1658322 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0562. Min Range: -5.0562
Max Act: 4.8062. Min Act: -0.1700
Data Index: 5417899 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0562. Min Range: -5.0562
Max Act: 4.8062. Min Act: -0.1700
Data Index: 3492938 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0562. Min Range: -5.0562
Max Act: 4.8062. Min Act: -0.1700
Data Index: 5132907 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0562. Min Range: -5.0562
Max Act: 4.8062. Min Act: -0.1700
Data Index: 5877542 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0562. Min Range: -5.0562
Max Act: 4.7749. Min Act: -0.1700
Data Index: 17175 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #19