Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1107 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2018. Min Range: -4.2018
Max Act: 4.2018. Min Act: -0.1700
Data Index: 4816901 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2018. Min Range: -4.2018
Max Act: 4.1393. Min Act: -0.1700
Data Index: 4077114 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2018. Min Range: -4.2018
Max Act: 4.0768. Min Act: -0.1700
Data Index: 4695545 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2018. Min Range: -4.2018
Max Act: 4.0768. Min Act: -0.1700
Data Index: 3274501 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2018. Min Range: -4.2018
Max Act: 4.0768. Min Act: -0.1700
Data Index: 5647479 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2018. Min Range: -4.2018
Max Act: 4.0768. Min Act: -0.1700
Data Index: 5715099 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2018. Min Range: -4.2018
Max Act: 4.0768. Min Act: -0.1700
Data Index: 5795967 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2018. Min Range: -4.2018
Max Act: 4.0768. Min Act: -0.1700
Data Index: 6142803 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2018. Min Range: -4.2018
Max Act: 4.0455. Min Act: -0.1700
Data Index: 1621543 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2018. Min Range: -4.2018
Max Act: 4.0142. Min Act: -0.1700
Data Index: 2904494 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2018. Min Range: -4.2018
Max Act: 4.0142. Min Act: -0.1694
Data Index: 8802971 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2018. Min Range: -4.2018
Max Act: 4.0142. Min Act: -0.1700
Data Index: 7946203 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2018. Min Range: -4.2018
Max Act: 4.0142. Min Act: -0.1700
Data Index: 7597638 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2018. Min Range: -4.2018
Max Act: 4.0455. Min Act: -0.1700
Data Index: 5995554 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2018. Min Range: -4.2018
Max Act: 4.0142. Min Act: -0.1700
Data Index: 2187199 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2018. Min Range: -4.2018
Max Act: 4.0142. Min Act: -0.1700
Data Index: 243047 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2018. Min Range: -4.2018
Max Act: 3.9830. Min Act: -0.1700
Data Index: 1429125 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2018. Min Range: -4.2018
Max Act: 3.9830. Min Act: -0.1699
Data Index: 1709797 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2018. Min Range: -4.2018
Max Act: 3.9830. Min Act: -0.1698
Data Index: 2467448 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2018. Min Range: -4.2018
Max Act: 3.9830. Min Act: -0.1700
Data Index: 1033587 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19