Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2674 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2099. Min Range: -4.2099
Max Act: 4.2099. Min Act: -0.1700
Data Index: 8699211 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2099. Min Range: -4.2099
Max Act: 4.2099. Min Act: -0.1700
Data Index: 5347689 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2099. Min Range: -4.2099
Max Act: 4.2099. Min Act: -0.1700
Data Index: 4747338 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2099. Min Range: -4.2099
Max Act: 4.2099. Min Act: -0.1700
Data Index: 2081947 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2099. Min Range: -4.2099
Max Act: 4.2099. Min Act: -0.1700
Data Index: 975577 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2099. Min Range: -4.2099
Max Act: 4.2099. Min Act: -0.1700
Data Index: 335999 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2099. Min Range: -4.2099
Max Act: 4.1787. Min Act: -0.1700
Data Index: 1996175 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2099. Min Range: -4.2099
Max Act: 4.1787. Min Act: -0.1700
Data Index: 1970326 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2099. Min Range: -4.2099
Max Act: 4.1787. Min Act: -0.1700
Data Index: 2976648 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2099. Min Range: -4.2099
Max Act: 4.1787. Min Act: -0.1700
Data Index: 59584 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2099. Min Range: -4.2099
Max Act: 4.1787. Min Act: -0.1700
Data Index: 4582221 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2099. Min Range: -4.2099
Max Act: 4.1787. Min Act: -0.1700
Data Index: 4472196 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2099. Min Range: -4.2099
Max Act: 4.1787. Min Act: -0.1700
Data Index: 1663463 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2099. Min Range: -4.2099
Max Act: 4.1787. Min Act: -0.1700
Data Index: 3996643 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2099. Min Range: -4.2099
Max Act: 4.1474. Min Act: -0.1700
Data Index: 3216060 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2099. Min Range: -4.2099
Max Act: 4.1787. Min Act: -0.1700
Data Index: 741751 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2099. Min Range: -4.2099
Max Act: 4.1787. Min Act: -0.1700
Data Index: 3119410 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2099. Min Range: -4.2099
Max Act: 4.1787. Min Act: -0.1700
Data Index: 2162440 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2099. Min Range: -4.2099
Max Act: 4.1787. Min Act: -0.1700
Data Index: 2050510 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2099. Min Range: -4.2099
Max Act: 4.1787. Min Act: -0.1700
Data Index: 1768962 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19