Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2134 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3996. Min Range: -6.3996
Max Act: 6.3996. Min Act: -0.1700
Data Index: 848909 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3996. Min Range: -6.3996
Max Act: 6.0559. Min Act: -0.1700
Data Index: 2525174 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3996. Min Range: -6.3996
Max Act: 6.0246. Min Act: -0.1700
Data Index: 4604077 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3996. Min Range: -6.3996
Max Act: 5.9621. Min Act: -0.1700
Data Index: 4109785 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3996. Min Range: -6.3996
Max Act: 5.9621. Min Act: -0.1700
Data Index: 2233076 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3996. Min Range: -6.3996
Max Act: 5.9621. Min Act: -0.1700
Data Index: 7262345 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3996. Min Range: -6.3996
Max Act: 5.8996. Min Act: -0.1700
Data Index: 3972303 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3996. Min Range: -6.3996
Max Act: 5.9309. Min Act: -0.1700
Data Index: 2981262 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3996. Min Range: -6.3996
Max Act: 5.8996. Min Act: -0.1700
Data Index: 5403977 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3996. Min Range: -6.3996
Max Act: 5.9309. Min Act: -0.1700
Data Index: 5558556 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3996. Min Range: -6.3996
Max Act: 5.8684. Min Act: -0.1700
Data Index: 4739831 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3996. Min Range: -6.3996
Max Act: 5.8684. Min Act: -0.1700
Data Index: 697008 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3996. Min Range: -6.3996
Max Act: 5.8684. Min Act: -0.1700
Data Index: 3972300 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3996. Min Range: -6.3996
Max Act: 5.8684. Min Act: -0.1700
Data Index: 5230531 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3996. Min Range: -6.3996
Max Act: 5.8996. Min Act: -0.1700
Data Index: 2890228 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3996. Min Range: -6.3996
Max Act: 5.8371. Min Act: -0.1700
Data Index: 3009934 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3996. Min Range: -6.3996
Max Act: 5.8371. Min Act: -0.1700
Data Index: 4748928 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3996. Min Range: -6.3996
Max Act: 5.8684. Min Act: -0.1700
Data Index: 761845 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3996. Min Range: -6.3996
Max Act: 5.8371. Min Act: -0.1700
Data Index: 1392000 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3996. Min Range: -6.3996
Max Act: 5.8059. Min Act: -0.1700
Data Index: 4175071 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #19