Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1782 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 10.5309. Min Range: -10.5309
Max Act: 10.5309. Min Act: -0.1700
Data Index: 415798 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5309. Min Range: -10.5309
Max Act: 10.2184. Min Act: -0.1700
Data Index: 415796 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5309. Min Range: -10.5309
Max Act: 10.2184. Min Act: -0.1700
Data Index: 7485868 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5309. Min Range: -10.5309
Max Act: 10.0934. Min Act: -0.1700
Data Index: 415795 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5309. Min Range: -10.5309
Max Act: 10.0934. Min Act: -0.1700
Data Index: 8083532 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5309. Min Range: -10.5309
Max Act: 10.0934. Min Act: -0.1700
Data Index: 1259298 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5309. Min Range: -10.5309
Max Act: 10.0309. Min Act: -0.1700
Data Index: 4886384 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5309. Min Range: -10.5309
Max Act: 10.0309. Min Act: -0.1700
Data Index: 3388330 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5309. Min Range: -10.5309
Max Act: 9.9684. Min Act: -0.1700
Data Index: 3622762 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5309. Min Range: -10.5309
Max Act: 9.9059. Min Act: -0.1700
Data Index: 936075 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5309. Min Range: -10.5309
Max Act: 9.9684. Min Act: -0.1700
Data Index: 4957190 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5309. Min Range: -10.5309
Max Act: 9.8434. Min Act: -0.1700
Data Index: 8675260 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5309. Min Range: -10.5309
Max Act: 9.8434. Min Act: -0.1700
Data Index: 4957167 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5309. Min Range: -10.5309
Max Act: 9.8434. Min Act: -0.1700
Data Index: 4957171 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5309. Min Range: -10.5309
Max Act: 9.8434. Min Act: -0.1700
Data Index: 3521737 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5309. Min Range: -10.5309
Max Act: 9.8434. Min Act: -0.1700
Data Index: 4416875 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5309. Min Range: -10.5309
Max Act: 9.7809. Min Act: -0.1700
Data Index: 7485869 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5309. Min Range: -10.5309
Max Act: 9.7809. Min Act: -0.1700
Data Index: 4582722 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5309. Min Range: -10.5309
Max Act: 9.8434. Min Act: -0.1700
Data Index: 3479581 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5309. Min Range: -10.5309
Max Act: 9.8434. Min Act: -0.1700
Data Index: 1925877 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #19