Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2121 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4577. Min Range: -5.4577
Max Act: 5.4577. Min Act: -0.1700
Data Index: 941643 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4577. Min Range: -5.4577
Max Act: 5.3952. Min Act: -0.1700
Data Index: 1087697 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4577. Min Range: -5.4577
Max Act: 5.3327. Min Act: -0.1700
Data Index: 5077810 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4577. Min Range: -5.4577
Max Act: 5.3014. Min Act: -0.1700
Data Index: 6919244 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4577. Min Range: -5.4577
Max Act: 5.3014. Min Act: -0.1700
Data Index: 4233045 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4577. Min Range: -5.4577
Max Act: 5.2077. Min Act: -0.1700
Data Index: 8171325 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4577. Min Range: -5.4577
Max Act: 5.2077. Min Act: -0.1700
Data Index: 3390568 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4577. Min Range: -5.4577
Max Act: 5.1764. Min Act: -0.1700
Data Index: 7407266 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4577. Min Range: -5.4577
Max Act: 5.1764. Min Act: -0.1700
Data Index: 2216321 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4577. Min Range: -5.4577
Max Act: 5.2077. Min Act: -0.1700
Data Index: 4588843 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4577. Min Range: -5.4577
Max Act: 5.1452. Min Act: -0.1700
Data Index: 4501609 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4577. Min Range: -5.4577
Max Act: 5.1139. Min Act: -0.1700
Data Index: 8214505 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4577. Min Range: -5.4577
Max Act: 5.1452. Min Act: -0.1700
Data Index: 6859109 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4577. Min Range: -5.4577
Max Act: 5.1139. Min Act: -0.1700
Data Index: 4581220 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4577. Min Range: -5.4577
Max Act: 5.1139. Min Act: -0.1700
Data Index: 7920228 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4577. Min Range: -5.4577
Max Act: 5.1139. Min Act: -0.1700
Data Index: 6025330 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4577. Min Range: -5.4577
Max Act: 5.0827. Min Act: -0.1700
Data Index: 4763761 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4577. Min Range: -5.4577
Max Act: 5.0827. Min Act: -0.1700
Data Index: 6824984 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4577. Min Range: -5.4577
Max Act: 5.0827. Min Act: -0.1700
Data Index: 188891 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4577. Min Range: -5.4577
Max Act: 5.0514. Min Act: -0.1700
Data Index: 5047174 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #19