Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3674 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 0.9791. Min Range: -0.9791
Max Act: 0.9791. Min Act: -0.1700
Data Index: 256623 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9791. Min Range: -0.9791
Max Act: 0.9791. Min Act: -0.1700
Data Index: 5211916 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9791. Min Range: -0.9791
Max Act: 0.9704. Min Act: -0.1700
Data Index: 598487 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9791. Min Range: -0.9791
Max Act: 0.9532. Min Act: -0.1700
Data Index: 660417 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9791. Min Range: -0.9791
Max Act: 0.9532. Min Act: -0.1700
Data Index: 2313600 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9791. Min Range: -0.9791
Max Act: 0.9532. Min Act: -0.1700
Data Index: 2104628 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9791. Min Range: -0.9791
Max Act: 0.9532. Min Act: -0.1700
Data Index: 7582079 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9791. Min Range: -0.9791
Max Act: 0.9532. Min Act: -0.1700
Data Index: 5008545 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9791. Min Range: -0.9791
Max Act: 0.9359. Min Act: -0.1700
Data Index: 471610 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9791. Min Range: -0.9791
Max Act: 0.9359. Min Act: -0.1700
Data Index: 4233158 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9791. Min Range: -0.9791
Max Act: 0.9359. Min Act: -0.1700
Data Index: 2898787 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9791. Min Range: -0.9791
Max Act: 0.9359. Min Act: -0.1700
Data Index: 5720130 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9791. Min Range: -0.9791
Max Act: 0.9359. Min Act: -0.1700
Data Index: 1943239 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9791. Min Range: -0.9791
Max Act: 0.9359. Min Act: -0.1700
Data Index: 4289402 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9791. Min Range: -0.9791
Max Act: 0.9273. Min Act: -0.1700
Data Index: 2722960 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9791. Min Range: -0.9791
Max Act: 0.9359. Min Act: -0.1700
Data Index: 4838696 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9791. Min Range: -0.9791
Max Act: 0.9273. Min Act: -0.1700
Data Index: 7635632 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9791. Min Range: -0.9791
Max Act: 0.9273. Min Act: -0.1700
Data Index: 7611807 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9791. Min Range: -0.9791
Max Act: 0.9273. Min Act: -0.1700
Data Index: 6817767 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9791. Min Range: -0.9791
Max Act: 0.9187. Min Act: -0.1700
Data Index: 1437190 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19