Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2380 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.0531. Min Range: -3.0531
Max Act: 3.0531. Min Act: -0.1700
Data Index: 326667 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0531. Min Range: -3.0531
Max Act: 3.0531. Min Act: -0.1700
Data Index: 1687626 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0531. Min Range: -3.0531
Max Act: 3.0373. Min Act: -0.1700
Data Index: 8475857 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0531. Min Range: -3.0531
Max Act: 3.0531. Min Act: -0.1700
Data Index: 5857203 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0531. Min Range: -3.0531
Max Act: 3.0373. Min Act: -0.1700
Data Index: 1274098 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0531. Min Range: -3.0531
Max Act: 3.0531. Min Act: -0.1700
Data Index: 7941311 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0531. Min Range: -3.0531
Max Act: 3.0057. Min Act: -0.1700
Data Index: 620462 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0531. Min Range: -3.0531
Max Act: 2.9899. Min Act: -0.1700
Data Index: 7646376 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0531. Min Range: -3.0531
Max Act: 3.0057. Min Act: -0.1700
Data Index: 4313830 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0531. Min Range: -3.0531
Max Act: 3.0057. Min Act: -0.1700
Data Index: 338667 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0531. Min Range: -3.0531
Max Act: 2.9741. Min Act: -0.1700
Data Index: 956551 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0531. Min Range: -3.0531
Max Act: 2.9899. Min Act: -0.1700
Data Index: 803049 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0531. Min Range: -3.0531
Max Act: 2.9899. Min Act: -0.1700
Data Index: 8224698 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0531. Min Range: -3.0531
Max Act: 2.9741. Min Act: -0.1700
Data Index: 4409923 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0531. Min Range: -3.0531
Max Act: 2.9741. Min Act: -0.1700
Data Index: 7065847 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0531. Min Range: -3.0531
Max Act: 2.9899. Min Act: -0.1700
Data Index: 863672 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0531. Min Range: -3.0531
Max Act: 2.9583. Min Act: -0.1700
Data Index: 4387551 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0531. Min Range: -3.0531
Max Act: 2.9741. Min Act: -0.1700
Data Index: 3209045 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0531. Min Range: -3.0531
Max Act: 2.9741. Min Act: -0.1700
Data Index: 2902999 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0531. Min Range: -3.0531
Max Act: 2.9583. Min Act: -0.1700
Data Index: 2337792 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #19