Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 650 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5824. Min Range: -4.5824
Max Act: 4.5824. Min Act: -0.1700
Data Index: 4385012 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5824. Min Range: -4.5824
Max Act: 4.4886. Min Act: -0.1700
Data Index: 6838960 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5824. Min Range: -4.5824
Max Act: 4.4886. Min Act: -0.1700
Data Index: 7336697 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5824. Min Range: -4.5824
Max Act: 4.4574. Min Act: -0.1700
Data Index: 407397 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5824. Min Range: -4.5824
Max Act: 4.4574. Min Act: -0.1700
Data Index: 5317469 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5824. Min Range: -4.5824
Max Act: 4.4261. Min Act: -0.1700
Data Index: 7630076 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5824. Min Range: -4.5824
Max Act: 4.4574. Min Act: -0.1700
Data Index: 4471247 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5824. Min Range: -4.5824
Max Act: 4.4261. Min Act: -0.1700
Data Index: 8687050 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5824. Min Range: -4.5824
Max Act: 4.4574. Min Act: -0.1700
Data Index: 2895538 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5824. Min Range: -4.5824
Max Act: 4.4261. Min Act: -0.1700
Data Index: 6364446 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5824. Min Range: -4.5824
Max Act: 4.3949. Min Act: -0.1700
Data Index: 1073067 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5824. Min Range: -4.5824
Max Act: 4.3949. Min Act: -0.1700
Data Index: 78640 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5824. Min Range: -4.5824
Max Act: 4.3636. Min Act: -0.1700
Data Index: 6459941 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5824. Min Range: -4.5824
Max Act: 4.4261. Min Act: -0.1700
Data Index: 1383060 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5824. Min Range: -4.5824
Max Act: 4.4261. Min Act: -0.1700
Data Index: 4991706 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5824. Min Range: -4.5824
Max Act: 4.3636. Min Act: -0.1700
Data Index: 2121461 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5824. Min Range: -4.5824
Max Act: 4.3636. Min Act: -0.1700
Data Index: 387985 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5824. Min Range: -4.5824
Max Act: 4.3323. Min Act: -0.1700
Data Index: 446046 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5824. Min Range: -4.5824
Max Act: 4.3636. Min Act: -0.1700
Data Index: 558600 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5824. Min Range: -4.5824
Max Act: 4.3323. Min Act: -0.1700
Data Index: 330859 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19