Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1883 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8327. Min Range: -4.8327
Max Act: 4.7702. Min Act: -0.1700
Data Index: 6865310 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8327. Min Range: -4.8327
Max Act: 4.8327. Min Act: -0.1700
Data Index: 3355160 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8327. Min Range: -4.8327
Max Act: 4.8014. Min Act: -0.1700
Data Index: 1944135 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8327. Min Range: -4.8327
Max Act: 4.7702. Min Act: -0.1700
Data Index: 7257703 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8327. Min Range: -4.8327
Max Act: 4.7702. Min Act: -0.1700
Data Index: 6076888 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8327. Min Range: -4.8327
Max Act: 4.6452. Min Act: -0.1700
Data Index: 2585057 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8327. Min Range: -4.8327
Max Act: 4.6452. Min Act: -0.1700
Data Index: 5045720 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8327. Min Range: -4.8327
Max Act: 4.6764. Min Act: -0.1700
Data Index: 2081577 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8327. Min Range: -4.8327
Max Act: 4.7077. Min Act: -0.1700
Data Index: 6767078 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8327. Min Range: -4.8327
Max Act: 4.6452. Min Act: -0.1700
Data Index: 8603982 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8327. Min Range: -4.8327
Max Act: 4.6764. Min Act: -0.1700
Data Index: 493616 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8327. Min Range: -4.8327
Max Act: 4.6764. Min Act: -0.1700
Data Index: 3642524 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8327. Min Range: -4.8327
Max Act: 4.6139. Min Act: -0.1700
Data Index: 8605784 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8327. Min Range: -4.8327
Max Act: 4.6452. Min Act: -0.1700
Data Index: 1453761 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8327. Min Range: -4.8327
Max Act: 4.6139. Min Act: -0.1700
Data Index: 3433932 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8327. Min Range: -4.8327
Max Act: 4.6452. Min Act: -0.1700
Data Index: 4245174 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8327. Min Range: -4.8327
Max Act: 4.5827. Min Act: -0.1700
Data Index: 4245152 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8327. Min Range: -4.8327
Max Act: 4.5827. Min Act: -0.1700
Data Index: 3780907 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8327. Min Range: -4.8327
Max Act: 4.5827. Min Act: -0.1700
Data Index: 4117255 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8327. Min Range: -4.8327
Max Act: 4.6139. Min Act: -0.1700
Data Index: 4117258 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #19