Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2722 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3870. Min Range: -4.3870
Max Act: 4.3870. Min Act: -0.1700
Data Index: 3525700 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3870. Min Range: -4.3870
Max Act: 4.2932. Min Act: -0.1700
Data Index: 4423020 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3870. Min Range: -4.3870
Max Act: 4.2932. Min Act: -0.1700
Data Index: 2089886 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3870. Min Range: -4.3870
Max Act: 4.2307. Min Act: -0.1700
Data Index: 5431045 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3870. Min Range: -4.3870
Max Act: 4.0744. Min Act: -0.1700
Data Index: 2532614 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3870. Min Range: -4.3870
Max Act: 4.0744. Min Act: -0.1700
Data Index: 496759 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3870. Min Range: -4.3870
Max Act: 4.0119. Min Act: -0.1700
Data Index: 6690227 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3870. Min Range: -4.3870
Max Act: 3.9807. Min Act: -0.1700
Data Index: 805292 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3870. Min Range: -4.3870
Max Act: 3.9807. Min Act: -0.1700
Data Index: 5400411 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3870. Min Range: -4.3870
Max Act: 3.9807. Min Act: -0.1700
Data Index: 5824781 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3870. Min Range: -4.3870
Max Act: 3.9181. Min Act: -0.1700
Data Index: 4523402 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3870. Min Range: -4.3870
Max Act: 3.9494. Min Act: -0.1700
Data Index: 1561609 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3870. Min Range: -4.3870
Max Act: 3.9181. Min Act: -0.1700
Data Index: 8173033 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3870. Min Range: -4.3870
Max Act: 3.8869. Min Act: -0.1700
Data Index: 4694215 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3870. Min Range: -4.3870
Max Act: 3.8087. Min Act: -0.1700
Data Index: 4287304 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3870. Min Range: -4.3870
Max Act: 3.8556. Min Act: -0.1700
Data Index: 809087 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3870. Min Range: -4.3870
Max Act: 3.7774. Min Act: -0.1700
Data Index: 6813979 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3870. Min Range: -4.3870
Max Act: 3.8869. Min Act: -0.1700
Data Index: 2661997 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3870. Min Range: -4.3870
Max Act: 3.7930. Min Act: -0.1700
Data Index: 1049504 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3870. Min Range: -4.3870
Max Act: 3.8087. Min Act: -0.1700
Data Index: 1665372 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #19